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

Dataset: Open Web Text

Neuron 2582 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: 4.0202. Min Range: -4.0202

Max Act: 4.0202. Min Act: -0.1700

Data Index: 3626300 (Open Web Text)

Max Activating Token Index: 184

Text #1

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.8857. Min Act: -0.1700

Data Index: 6445274 (Open Web Text)

Max Activating Token Index: 100

Text #2

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.8251. Min Act: -0.1700

Data Index: 7122992 (Open Web Text)

Max Activating Token Index: 724

Text #3

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.8225. Min Act: -0.1700

Data Index: 4472243 (Open Web Text)

Max Activating Token Index: 452

Text #4

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.8135. Min Act: -0.1700

Data Index: 8496593 (Open Web Text)

Max Activating Token Index: 87

Text #5

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.8199. Min Act: -0.1700

Data Index: 2319351 (Open Web Text)

Max Activating Token Index: 805

Text #6

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.8380. Min Act: -0.1700

Data Index: 2813692 (Open Web Text)

Max Activating Token Index: 823

Text #7

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.7990. Min Act: -0.1700

Data Index: 6884866 (Open Web Text)

Max Activating Token Index: 463

Text #8

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.7944. Min Act: -0.1700

Data Index: 7396900 (Open Web Text)

Max Activating Token Index: 199

Text #9

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.7905. Min Act: -0.1700

Data Index: 3901650 (Open Web Text)

Max Activating Token Index: 621

Text #10

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.8087. Min Act: -0.1700

Data Index: 4820153 (Open Web Text)

Max Activating Token Index: 1001

Text #11

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.7492. Min Act: -0.1700

Data Index: 864624 (Open Web Text)

Max Activating Token Index: 753

Text #12

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.7932. Min Act: -0.1700

Data Index: 4090078 (Open Web Text)

Max Activating Token Index: 566

Text #13

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.7651. Min Act: -0.1700

Data Index: 8618144 (Open Web Text)

Max Activating Token Index: 134

Text #14

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.7121. Min Act: -0.1700

Data Index: 1158013 (Open Web Text)

Max Activating Token Index: 275

Text #15

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.7419. Min Act: -0.1700

Data Index: 4481739 (Open Web Text)

Max Activating Token Index: 675

Text #16

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.7195. Min Act: -0.1700

Data Index: 1250857 (Open Web Text)

Max Activating Token Index: 971

Text #17

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.7403. Min Act: -0.1700

Data Index: 6872517 (Open Web Text)

Max Activating Token Index: 261

Text #18

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.7487. Min Act: -0.1700

Data Index: 6645735 (Open Web Text)

Max Activating Token Index: 303

Text #19

Max Range: 4.0202. Min Range: -4.0202

Max Act: 3.7620. Min Act: -0.1700

Data Index: 3381906 (Open Web Text)

Max Activating Token Index: 580