< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1710 in Layer 1

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: 2.9707. Min Range: -2.9707

Max Act: 2.9707. Min Act: -0.1700

Data Index: 1133089 (Open Web Text)

Max Activating Token Index: 724

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.7981. Min Act: -0.1700

Data Index: 8702020 (Open Web Text)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.7743. Min Act: -0.1700

Data Index: 4268883 (Open Web Text)

Max Activating Token Index: 23

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.7228. Min Act: -0.1700

Data Index: 4743190 (Open Web Text)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.7236. Min Act: -0.1700

Data Index: 1293353 (Open Web Text)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.7070. Min Act: -0.1700

Data Index: 116208 (Open Web Text)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.7089. Min Act: -0.1700

Data Index: 198840 (Open Web Text)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.6831. Min Act: -0.1700

Data Index: 4267834 (Open Web Text)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.6830. Min Act: -0.1700

Data Index: 1927010 (Open Web Text)

Max Activating Token Index: 225

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.6920. Min Act: -0.1700

Data Index: 8167267 (Open Web Text)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.7004. Min Act: -0.1700

Data Index: 7844495 (Open Web Text)

Max Activating Token Index: 382

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.6884. Min Act: -0.1700

Data Index: 7656414 (Open Web Text)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.6664. Min Act: -0.1700

Data Index: 7889109 (Open Web Text)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.6674. Min Act: -0.1700

Data Index: 53177 (Open Web Text)

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.6505. Min Act: -0.1700

Data Index: 2529484 (Open Web Text)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.6653. Min Act: -0.1700

Data Index: 2229684 (Open Web Text)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.6435. Min Act: -0.1700

Data Index: 7283198 (Open Web Text)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.6544. Min Act: -0.1700

Data Index: 6434073 (Open Web Text)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.6475. Min Act: -0.1700

Data Index: 3826547 (Open Web Text)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9707. Min Range: -2.9707

Max Act: 2.6461. Min Act: -0.1700

Data Index: 2784714 (Open Web Text)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #19