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

Dataset: Open Web Text

Neuron 2535 in Layer 2

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: 2.3108. Min Range: -2.3108

Max Act: 2.3108. Min Act: -0.1700

Data Index: 5470779 (Open Web Text)

Max Activating Token Index: 67

Text #1

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2893. Min Act: -0.1700

Data Index: 5165792 (Open Web Text)

Max Activating Token Index: 723

Text #2

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2803. Min Act: -0.1700

Data Index: 1952425 (Open Web Text)

Max Activating Token Index: 138

Text #3

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2783. Min Act: -0.1700

Data Index: 1372963 (Open Web Text)

Max Activating Token Index: 643

Text #4

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2803. Min Act: -0.1700

Data Index: 2076872 (Open Web Text)

Max Activating Token Index: 158

Text #5

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2491. Min Act: -0.1700

Data Index: 4580566 (Open Web Text)

Max Activating Token Index: 518

Text #6

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2398. Min Act: -0.1700

Data Index: 4659886 (Open Web Text)

Max Activating Token Index: 477

Text #7

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2432. Min Act: -0.1700

Data Index: 2964764 (Open Web Text)

Max Activating Token Index: 60

Text #8

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2526. Min Act: -0.1700

Data Index: 5653633 (Open Web Text)

Max Activating Token Index: 149

Text #9

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2687. Min Act: -0.1700

Data Index: 6913835 (Open Web Text)

Max Activating Token Index: 634

Text #10

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2274. Min Act: -0.1700

Data Index: 6546422 (Open Web Text)

Max Activating Token Index: 982

Text #11

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2234. Min Act: -0.1700

Data Index: 6023688 (Open Web Text)

Max Activating Token Index: 259

Text #12

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2328. Min Act: -0.1700

Data Index: 5302387 (Open Web Text)

Max Activating Token Index: 259

Text #13

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2389. Min Act: -0.1700

Data Index: 638728 (Open Web Text)

Max Activating Token Index: 64

Text #14

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2280. Min Act: -0.1700

Data Index: 3233081 (Open Web Text)

Max Activating Token Index: 309

Text #15

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2280. Min Act: -0.1700

Data Index: 7135842 (Open Web Text)

Max Activating Token Index: 59

Text #16

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2430. Min Act: -0.1700

Data Index: 584484 (Open Web Text)

Max Activating Token Index: 228

Text #17

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2347. Min Act: -0.1700

Data Index: 2145939 (Open Web Text)

Max Activating Token Index: 848

Text #18

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2229. Min Act: -0.1700

Data Index: 2240342 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2285. Min Act: -0.1700

Data Index: 5940646 (Open Web Text)

Max Activating Token Index: 493