< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 705 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: 2.3184. Min Range: -2.3184

Max Act: 2.3184. Min Act: -0.1700

Data Index: 7377427 (Open Web Text)

Max Activating Token Index: 111

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.2761. Min Act: -0.1700

Data Index: 2083067 (Open Web Text)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.2773. Min Act: -0.1700

Data Index: 3620384 (Open Web Text)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.2734. Min Act: -0.1700

Data Index: 4519511 (Open Web Text)

Max Activating Token Index: 59

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.2615. Min Act: -0.1700

Data Index: 4295914 (Open Web Text)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.2830. Min Act: -0.1700

Data Index: 4377160 (Open Web Text)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.2379. Min Act: -0.1700

Data Index: 4875364 (Open Web Text)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.2556. Min Act: -0.1700

Data Index: 2998846 (Open Web Text)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.2651. Min Act: -0.1700

Data Index: 7580676 (Open Web Text)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.2464. Min Act: -0.1700

Data Index: 7201720 (Open Web Text)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.2359. Min Act: -0.1700

Data Index: 2916687 (Open Web Text)

Max Activating Token Index: 620

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.2352. Min Act: -0.1700

Data Index: 6939175 (Open Web Text)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.1989. Min Act: -0.1700

Data Index: 8454872 (Open Web Text)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.2000. Min Act: -0.1700

Data Index: 2991242 (Open Web Text)

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.1992. Min Act: -0.1700

Data Index: 8539680 (Open Web Text)

Max Activating Token Index: 200

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.2053. Min Act: -0.1700

Data Index: 7930402 (Open Web Text)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.2141. Min Act: -0.1700

Data Index: 6164750 (Open Web Text)

Max Activating Token Index: 623

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.2081. Min Act: -0.1700

Data Index: 2587897 (Open Web Text)

Max Activating Token Index: 354

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.1910. Min Act: -0.1700

Data Index: 2479424 (Open Web Text)

Max Activating Token Index: 912

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.3184. Min Range: -2.3184

Max Act: 2.1990. Min Act: -0.1700

Data Index: 625273 (Open Web Text)

Max Activating Token Index: 949

Click toggle to see full text

Truncated

Full Text #19