< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2533 in Layer 4

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: 2.0982. Min Range: -2.0982

Max Act: 2.0982. Min Act: -0.1700

Data Index: 1388983 (Open Web Text)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.0982. Min Range: -2.0982

Max Act: 2.0543. Min Act: -0.1700

Data Index: 1215347 (Open Web Text)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.0982. Min Range: -2.0982

Max Act: 2.0545. Min Act: -0.1700

Data Index: 4781427 (Open Web Text)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.0982. Min Range: -2.0982

Max Act: 2.0399. Min Act: -0.1700

Data Index: 8620386 (Open Web Text)

Max Activating Token Index: 192

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.0982. Min Range: -2.0982

Max Act: 2.0364. Min Act: -0.1700

Data Index: 932698 (Open Web Text)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.0982. Min Range: -2.0982

Max Act: 2.0247. Min Act: -0.1700

Data Index: 7507764 (Open Web Text)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.0982. Min Range: -2.0982

Max Act: 2.0272. Min Act: -0.1700

Data Index: 6056331 (Open Web Text)

Max Activating Token Index: 473

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.0982. Min Range: -2.0982

Max Act: 2.0109. Min Act: -0.1700

Data Index: 1237980 (Open Web Text)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.0982. Min Range: -2.0982

Max Act: 2.0094. Min Act: -0.1700

Data Index: 3890959 (Open Web Text)

Max Activating Token Index: 357

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.0982. Min Range: -2.0982

Max Act: 1.9930. Min Act: -0.1700

Data Index: 1711529 (Open Web Text)

Max Activating Token Index: 149

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.0982. Min Range: -2.0982

Max Act: 1.9960. Min Act: -0.1700

Data Index: 4640114 (Open Web Text)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.0982. Min Range: -2.0982

Max Act: 1.9866. Min Act: -0.1700

Data Index: 3503995 (Open Web Text)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.0982. Min Range: -2.0982

Max Act: 2.0067. Min Act: -0.1700

Data Index: 8112407 (Open Web Text)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.0982. Min Range: -2.0982

Max Act: 1.9810. Min Act: -0.1700

Data Index: 7134526 (Open Web Text)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.0982. Min Range: -2.0982

Max Act: 1.9925. Min Act: -0.1700

Data Index: 2194408 (Open Web Text)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.0982. Min Range: -2.0982

Max Act: 1.9848. Min Act: -0.1700

Data Index: 151620 (Open Web Text)

Max Activating Token Index: 328

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.0982. Min Range: -2.0982

Max Act: 1.9813. Min Act: -0.1699

Data Index: 8122583 (Open Web Text)

Max Activating Token Index: 218

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.0982. Min Range: -2.0982

Max Act: 1.9645. Min Act: -0.1700

Data Index: 7601068 (Open Web Text)

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.0982. Min Range: -2.0982

Max Act: 1.9625. Min Act: -0.1700

Data Index: 1269958 (Open Web Text)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.0982. Min Range: -2.0982

Max Act: 1.9770. Min Act: -0.1700

Data Index: 6782326 (Open Web Text)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #19