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

Dataset: Open Web Text

Neuron 520 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: 4.9297. Min Range: -4.9297

Max Act: 4.9297. Min Act: -0.1700

Data Index: 7172048 (Open Web Text)

Max Activating Token Index: 193

Text #1

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.8320. Min Act: -0.1700

Data Index: 4806125 (Open Web Text)

Max Activating Token Index: 757

Text #2

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.7485. Min Act: -0.1700

Data Index: 8574669 (Open Web Text)

Max Activating Token Index: 240

Text #3

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.7053. Min Act: -0.1700

Data Index: 7342279 (Open Web Text)

Max Activating Token Index: 433

Text #4

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.7205. Min Act: -0.1700

Data Index: 4601439 (Open Web Text)

Max Activating Token Index: 274

Text #5

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.7130. Min Act: -0.1700

Data Index: 754738 (Open Web Text)

Max Activating Token Index: 997

Text #6

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.7176. Min Act: -0.1700

Data Index: 5959637 (Open Web Text)

Max Activating Token Index: 240

Text #7

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.6721. Min Act: -0.1700

Data Index: 4656710 (Open Web Text)

Max Activating Token Index: 262

Text #8

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.6774. Min Act: -0.1700

Data Index: 7231230 (Open Web Text)

Max Activating Token Index: 411

Text #9

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.6631. Min Act: -0.1700

Data Index: 1031299 (Open Web Text)

Max Activating Token Index: 979

Text #10

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.6580. Min Act: -0.1700

Data Index: 2816761 (Open Web Text)

Max Activating Token Index: 992

Text #11

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.6644. Min Act: -0.1700

Data Index: 4891489 (Open Web Text)

Max Activating Token Index: 753

Text #12

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.6196. Min Act: -0.1700

Data Index: 1372587 (Open Web Text)

Max Activating Token Index: 641

Text #13

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.6324. Min Act: -0.1700

Data Index: 820988 (Open Web Text)

Max Activating Token Index: 296

Text #14

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.5894. Min Act: -0.1700

Data Index: 3166127 (Open Web Text)

Max Activating Token Index: 427

Text #15

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.6516. Min Act: -0.1700

Data Index: 5356660 (Open Web Text)

Max Activating Token Index: 892

Text #16

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.5433. Min Act: -0.1700

Data Index: 3183488 (Open Web Text)

Max Activating Token Index: 113

Text #17

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.5600. Min Act: -0.1700

Data Index: 865223 (Open Web Text)

Max Activating Token Index: 821

Text #18

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.5547. Min Act: -0.1700

Data Index: 3166793 (Open Web Text)

Max Activating Token Index: 658

Text #19

Max Range: 4.9297. Min Range: -4.9297

Max Act: 4.5287. Min Act: -0.1700

Data Index: 4383261 (Open Web Text)

Max Activating Token Index: 126