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

Dataset: Open Web Text

Neuron 2638 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: 1.9364. Min Range: -1.9364

Max Act: 1.9364. Min Act: -0.1700

Data Index: 3823075 (Open Web Text)

Max Activating Token Index: 78

Text #1

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8843. Min Act: -0.1700

Data Index: 3250910 (Open Web Text)

Max Activating Token Index: 29

Text #2

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8852. Min Act: -0.1700

Data Index: 8746679 (Open Web Text)

Max Activating Token Index: 204

Text #3

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8609. Min Act: -0.1700

Data Index: 1943914 (Open Web Text)

Max Activating Token Index: 31

Text #4

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8419. Min Act: -0.1700

Data Index: 458786 (Open Web Text)

Max Activating Token Index: 111

Text #5

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8399. Min Act: -0.1700

Data Index: 5810220 (Open Web Text)

Max Activating Token Index: 35

Text #6

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8456. Min Act: -0.1700

Data Index: 932210 (Open Web Text)

Max Activating Token Index: 60

Text #7

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8530. Min Act: -0.1700

Data Index: 6553987 (Open Web Text)

Max Activating Token Index: 47

Text #8

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8363. Min Act: -0.1700

Data Index: 8205885 (Open Web Text)

Max Activating Token Index: 253

Text #9

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8257. Min Act: -0.1700

Data Index: 2239641 (Open Web Text)

Max Activating Token Index: 37

Text #10

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8369. Min Act: -0.1700

Data Index: 929225 (Open Web Text)

Max Activating Token Index: 669

Text #11

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8251. Min Act: -0.1700

Data Index: 2279173 (Open Web Text)

Max Activating Token Index: 787

Text #12

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8253. Min Act: -0.1700

Data Index: 7792857 (Open Web Text)

Max Activating Token Index: 853

Text #13

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8156. Min Act: -0.1700

Data Index: 3425006 (Open Web Text)

Max Activating Token Index: 252

Text #14

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8072. Min Act: -0.1700

Data Index: 4744632 (Open Web Text)

Max Activating Token Index: 58

Text #15

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8173. Min Act: -0.1700

Data Index: 1269756 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8159. Min Act: -0.1700

Data Index: 4433940 (Open Web Text)

Max Activating Token Index: 180

Text #17

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8195. Min Act: -0.1700

Data Index: 1111017 (Open Web Text)

Max Activating Token Index: 456

Text #18

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.8139. Min Act: -0.1700

Data Index: 175877 (Open Web Text)

Max Activating Token Index: 379

Text #19

Max Range: 1.9364. Min Range: -1.9364

Max Act: 1.7974. Min Act: -0.1700

Data Index: 2967026 (Open Web Text)

Max Activating Token Index: 890