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

Dataset: Open Web Text

Neuron 2279 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: 3.5027. Min Range: -3.5027

Max Act: 3.5027. Min Act: -0.1700

Data Index: 3996564 (Open Web Text)

Max Activating Token Index: 791

Text #1

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.4238. Min Act: -0.1700

Data Index: 4367391 (Open Web Text)

Max Activating Token Index: 543

Text #2

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.3581. Min Act: -0.1700

Data Index: 6190282 (Open Web Text)

Max Activating Token Index: 431

Text #3

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.3439. Min Act: -0.1700

Data Index: 4367386 (Open Web Text)

Max Activating Token Index: 770

Text #4

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.3196. Min Act: -0.1700

Data Index: 4783917 (Open Web Text)

Max Activating Token Index: 253

Text #5

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.3385. Min Act: -0.1700

Data Index: 8572361 (Open Web Text)

Max Activating Token Index: 507

Text #6

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.2835. Min Act: -0.1700

Data Index: 7631102 (Open Web Text)

Max Activating Token Index: 348

Text #7

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.3159. Min Act: -0.1700

Data Index: 5242774 (Open Web Text)

Max Activating Token Index: 505

Text #8

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.2686. Min Act: -0.1700

Data Index: 6002863 (Open Web Text)

Max Activating Token Index: 689

Text #9

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.2741. Min Act: -0.1700

Data Index: 6772528 (Open Web Text)

Max Activating Token Index: 956

Text #10

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.2886. Min Act: -0.1700

Data Index: 2141923 (Open Web Text)

Max Activating Token Index: 787

Text #11

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.3006. Min Act: -0.1700

Data Index: 7116929 (Open Web Text)

Max Activating Token Index: 305

Text #12

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.2773. Min Act: -0.1700

Data Index: 6641236 (Open Web Text)

Max Activating Token Index: 174

Text #13

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.2695. Min Act: -0.1700

Data Index: 8430813 (Open Web Text)

Max Activating Token Index: 404

Text #14

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.2628. Min Act: -0.1700

Data Index: 7929254 (Open Web Text)

Max Activating Token Index: 399

Text #15

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.2638. Min Act: -0.1700

Data Index: 3337914 (Open Web Text)

Max Activating Token Index: 1012

Text #16

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.2411. Min Act: -0.1700

Data Index: 2044709 (Open Web Text)

Max Activating Token Index: 135

Text #17

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.2555. Min Act: -0.1700

Data Index: 7342192 (Open Web Text)

Max Activating Token Index: 48

Text #18

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.2454. Min Act: -0.1700

Data Index: 8121200 (Open Web Text)

Max Activating Token Index: 194

Text #19

Max Range: 3.5027. Min Range: -3.5027

Max Act: 3.2170. Min Act: -0.1700

Data Index: 5075399 (Open Web Text)

Max Activating Token Index: 175