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

Dataset: Open Web Text

Neuron 1325 in Layer 6

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: 6.3678. Min Range: -6.3678

Max Act: 6.3155. Min Act: -0.1700

Data Index: 5803952 (Open Web Text)

Max Activating Token Index: 398

Text #1

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.3678. Min Act: -0.1700

Data Index: 1297778 (Open Web Text)

Max Activating Token Index: 925

Text #2

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.2513. Min Act: -0.1700

Data Index: 7056704 (Open Web Text)

Max Activating Token Index: 251

Text #3

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.2654. Min Act: -0.1700

Data Index: 841395 (Open Web Text)

Max Activating Token Index: 153

Text #4

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.2370. Min Act: -0.1700

Data Index: 1581454 (Open Web Text)

Max Activating Token Index: 75

Text #5

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.2305. Min Act: -0.1700

Data Index: 8358353 (Open Web Text)

Max Activating Token Index: 802

Text #6

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.2196. Min Act: -0.1700

Data Index: 6750345 (Open Web Text)

Max Activating Token Index: 659

Text #7

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.2234. Min Act: -0.1700

Data Index: 2848733 (Open Web Text)

Max Activating Token Index: 430

Text #8

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.1872. Min Act: -0.1700

Data Index: 4460826 (Open Web Text)

Max Activating Token Index: 625

Text #9

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.1853. Min Act: -0.1700

Data Index: 4464795 (Open Web Text)

Max Activating Token Index: 317

Text #10

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.2151. Min Act: -0.1700

Data Index: 3789873 (Open Web Text)

Max Activating Token Index: 296

Text #11

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.2088. Min Act: -0.1700

Data Index: 1732544 (Open Web Text)

Max Activating Token Index: 967

Text #12

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.1856. Min Act: -0.1700

Data Index: 3655910 (Open Web Text)

Max Activating Token Index: 807

Text #13

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.2293. Min Act: -0.1700

Data Index: 17791 (Open Web Text)

Max Activating Token Index: 977

Text #14

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.1689. Min Act: -0.1700

Data Index: 1681002 (Open Web Text)

Max Activating Token Index: 272

Text #15

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.1895. Min Act: -0.1700

Data Index: 1195647 (Open Web Text)

Max Activating Token Index: 859

Text #16

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.1973. Min Act: -0.1700

Data Index: 6750342 (Open Web Text)

Max Activating Token Index: 690

Text #17

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.1651. Min Act: -0.1700

Data Index: 8254420 (Open Web Text)

Max Activating Token Index: 329

Text #18

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.2041. Min Act: -0.1700

Data Index: 2985385 (Open Web Text)

Max Activating Token Index: 351

Text #19

Max Range: 6.3678. Min Range: -6.3678

Max Act: 6.1852. Min Act: -0.1700

Data Index: 4116262 (Open Web Text)

Max Activating Token Index: 118