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

Dataset: Open Web Text

Neuron 521 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: 3.5053. Min Range: -3.5053

Max Act: 3.5053. Min Act: -0.1700

Data Index: 1224524 (Open Web Text)

Max Activating Token Index: 458

Text #1

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.4384. Min Act: -0.1700

Data Index: 3760002 (Open Web Text)

Max Activating Token Index: 156

Text #2

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.3965. Min Act: -0.1700

Data Index: 1866135 (Open Web Text)

Max Activating Token Index: 777

Text #3

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.3072. Min Act: -0.1700

Data Index: 1654936 (Open Web Text)

Max Activating Token Index: 481

Text #4

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.3025. Min Act: -0.1700

Data Index: 2093491 (Open Web Text)

Max Activating Token Index: 960

Text #5

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.2727. Min Act: -0.1700

Data Index: 5983170 (Open Web Text)

Max Activating Token Index: 284

Text #6

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.2793. Min Act: -0.1700

Data Index: 1705336 (Open Web Text)

Max Activating Token Index: 220

Text #7

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.2916. Min Act: -0.1700

Data Index: 5506476 (Open Web Text)

Max Activating Token Index: 735

Text #8

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.2617. Min Act: -0.1700

Data Index: 2879781 (Open Web Text)

Max Activating Token Index: 590

Text #9

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.2597. Min Act: -0.1700

Data Index: 4551750 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.2579. Min Act: -0.1700

Data Index: 5551135 (Open Web Text)

Max Activating Token Index: 507

Text #11

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.2426. Min Act: -0.1700

Data Index: 3402029 (Open Web Text)

Max Activating Token Index: 256

Text #12

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.2370. Min Act: -0.1700

Data Index: 5551138 (Open Web Text)

Max Activating Token Index: 629

Text #13

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.2362. Min Act: -0.1700

Data Index: 3556019 (Open Web Text)

Max Activating Token Index: 413

Text #14

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.2374. Min Act: -0.1700

Data Index: 5965245 (Open Web Text)

Max Activating Token Index: 347

Text #15

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.2323. Min Act: -0.1700

Data Index: 8048839 (Open Web Text)

Max Activating Token Index: 185

Text #16

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.1933. Min Act: -0.1700

Data Index: 2330043 (Open Web Text)

Max Activating Token Index: 793

Text #17

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.1959. Min Act: -0.1700

Data Index: 5983167 (Open Web Text)

Max Activating Token Index: 162

Text #18

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.2335. Min Act: -0.1700

Data Index: 615285 (Open Web Text)

Max Activating Token Index: 863

Text #19

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.2112. Min Act: -0.1700

Data Index: 3109639 (Open Web Text)

Max Activating Token Index: 778