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

Dataset: Open Web Text

Neuron 139 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: 4.6007. Min Range: -4.6007

Max Act: 4.5953. Min Act: -0.1700

Data Index: 561814 (Open Web Text)

Max Activating Token Index: 643

Text #1

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.6007. Min Act: -0.1700

Data Index: 3772772 (Open Web Text)

Max Activating Token Index: 143

Text #2

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.5277. Min Act: -0.1700

Data Index: 816482 (Open Web Text)

Max Activating Token Index: 494

Text #3

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.4942. Min Act: -0.1700

Data Index: 2056505 (Open Web Text)

Max Activating Token Index: 502

Text #4

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.4593. Min Act: -0.1700

Data Index: 4805796 (Open Web Text)

Max Activating Token Index: 210

Text #5

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.4749. Min Act: -0.1700

Data Index: 8596537 (Open Web Text)

Max Activating Token Index: 224

Text #6

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.4743. Min Act: -0.1700

Data Index: 7792569 (Open Web Text)

Max Activating Token Index: 418

Text #7

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.4333. Min Act: -0.1700

Data Index: 7506125 (Open Web Text)

Max Activating Token Index: 911

Text #8

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.4612. Min Act: -0.1700

Data Index: 1373122 (Open Web Text)

Max Activating Token Index: 674

Text #9

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.4473. Min Act: -0.1700

Data Index: 4289599 (Open Web Text)

Max Activating Token Index: 211

Text #10

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.4438. Min Act: -0.1700

Data Index: 1372058 (Open Web Text)

Max Activating Token Index: 509

Text #11

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.4490. Min Act: -0.1700

Data Index: 5122890 (Open Web Text)

Max Activating Token Index: 518

Text #12

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.4235. Min Act: -0.1700

Data Index: 6182080 (Open Web Text)

Max Activating Token Index: 318

Text #13

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.4016. Min Act: -0.1700

Data Index: 6685045 (Open Web Text)

Max Activating Token Index: 205

Text #14

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.4306. Min Act: -0.1700

Data Index: 5268417 (Open Web Text)

Max Activating Token Index: 996

Text #15

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.4063. Min Act: -0.1700

Data Index: 382630 (Open Web Text)

Max Activating Token Index: 542

Text #16

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.4168. Min Act: -0.1700

Data Index: 3934313 (Open Web Text)

Max Activating Token Index: 374

Text #17

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.3677. Min Act: -0.1700

Data Index: 3617419 (Open Web Text)

Max Activating Token Index: 707

Text #18

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.3817. Min Act: -0.1700

Data Index: 4466968 (Open Web Text)

Max Activating Token Index: 187

Text #19

Max Range: 4.6007. Min Range: -4.6007

Max Act: 4.3622. Min Act: -0.1700

Data Index: 1270552 (Open Web Text)

Max Activating Token Index: 987