< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1855 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.8792. Min Act: -0.1700

Data Index: 8692906 (Open Web Text)

Max Activating Token Index: 281

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.8917. Min Act: -0.1700

Data Index: 6573787 (Open Web Text)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7954. Min Act: -0.1700

Data Index: 2033605 (Open Web Text)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7626. Min Act: -0.1700

Data Index: 7709407 (Open Web Text)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7621. Min Act: -0.1700

Data Index: 178110 (Open Web Text)

Max Activating Token Index: 335

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7714. Min Act: -0.1700

Data Index: 3375795 (Open Web Text)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7624. Min Act: -0.1700

Data Index: 8441428 (Open Web Text)

Max Activating Token Index: 846

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7602. Min Act: -0.1700

Data Index: 2146028 (Open Web Text)

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7518. Min Act: -0.1700

Data Index: 7200209 (Open Web Text)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7426. Min Act: -0.1700

Data Index: 7156574 (Open Web Text)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7284. Min Act: -0.1700

Data Index: 3045968 (Open Web Text)

Max Activating Token Index: 765

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7240. Min Act: -0.1700

Data Index: 8293599 (Open Web Text)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7387. Min Act: -0.1700

Data Index: 3543541 (Open Web Text)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7356. Min Act: -0.1700

Data Index: 4879960 (Open Web Text)

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7532. Min Act: -0.1700

Data Index: 1877770 (Open Web Text)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7330. Min Act: -0.1700

Data Index: 2647181 (Open Web Text)

Max Activating Token Index: 207

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7404. Min Act: -0.1700

Data Index: 6200346 (Open Web Text)

Max Activating Token Index: 430

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7286. Min Act: -0.1700

Data Index: 2274743 (Open Web Text)

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7179. Min Act: -0.1700

Data Index: 7698366 (Open Web Text)

Max Activating Token Index: 402

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8917. Min Range: -2.8917

Max Act: 2.7211. Min Act: -0.1700

Data Index: 819543 (Open Web Text)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #19