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

Dataset: Open Web Text

Neuron 1919 in Layer 5

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: 3.3575. Min Range: -3.3575

Max Act: 3.3575. Min Act: -0.1700

Data Index: 344722 (Open Web Text)

Max Activating Token Index: 622

Text #1

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.2227. Min Act: -0.1700

Data Index: 5362741 (Open Web Text)

Max Activating Token Index: 566

Text #2

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.2047. Min Act: -0.1700

Data Index: 38627 (Open Web Text)

Max Activating Token Index: 262

Text #3

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.2034. Min Act: -0.1700

Data Index: 1328732 (Open Web Text)

Max Activating Token Index: 614

Text #4

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.1593. Min Act: -0.1700

Data Index: 8493282 (Open Web Text)

Max Activating Token Index: 92

Text #5

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.1673. Min Act: -0.1700

Data Index: 6318 (Open Web Text)

Max Activating Token Index: 182

Text #6

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.1546. Min Act: -0.1700

Data Index: 157678 (Open Web Text)

Max Activating Token Index: 311

Text #7

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.1293. Min Act: -0.1700

Data Index: 5739239 (Open Web Text)

Max Activating Token Index: 628

Text #8

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.1231. Min Act: -0.1700

Data Index: 172617 (Open Web Text)

Max Activating Token Index: 36

Text #9

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.1229. Min Act: -0.1700

Data Index: 3168191 (Open Web Text)

Max Activating Token Index: 411

Text #10

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.0744. Min Act: -0.1700

Data Index: 5672895 (Open Web Text)

Max Activating Token Index: 560

Text #11

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.1289. Min Act: -0.1700

Data Index: 1372555 (Open Web Text)

Max Activating Token Index: 114

Text #12

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.0945. Min Act: -0.1700

Data Index: 3487543 (Open Web Text)

Max Activating Token Index: 664

Text #13

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.0655. Min Act: -0.1700

Data Index: 8715339 (Open Web Text)

Max Activating Token Index: 822

Text #14

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.0737. Min Act: -0.1700

Data Index: 5219390 (Open Web Text)

Max Activating Token Index: 846

Text #15

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.0632. Min Act: -0.1700

Data Index: 5760341 (Open Web Text)

Max Activating Token Index: 436

Text #16

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.0685. Min Act: -0.1700

Data Index: 5429487 (Open Web Text)

Max Activating Token Index: 539

Text #17

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.0139. Min Act: -0.1700

Data Index: 3483968 (Open Web Text)

Max Activating Token Index: 963

Text #18

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.0518. Min Act: -0.1700

Data Index: 1845996 (Open Web Text)

Max Activating Token Index: 128

Text #19

Max Range: 3.3575. Min Range: -3.3575

Max Act: 3.0566. Min Act: -0.1700

Data Index: 8352610 (Open Web Text)

Max Activating Token Index: 480