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

Dataset: Open Web Text

Neuron 2148 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: 4.7340. Min Range: -4.7340

Max Act: 4.7340. Min Act: -0.1700

Data Index: 2651007 (Open Web Text)

Max Activating Token Index: 30

Text #1

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.6329. Min Act: -0.1700

Data Index: 6166354 (Open Web Text)

Max Activating Token Index: 43

Text #2

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.5969. Min Act: -0.1700

Data Index: 921544 (Open Web Text)

Max Activating Token Index: 681

Text #3

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.4181. Min Act: -0.1700

Data Index: 8692897 (Open Web Text)

Max Activating Token Index: 403

Text #4

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.4209. Min Act: -0.1700

Data Index: 5984378 (Open Web Text)

Max Activating Token Index: 503

Text #5

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.4159. Min Act: -0.1700

Data Index: 6434443 (Open Web Text)

Max Activating Token Index: 687

Text #6

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.4165. Min Act: -0.1700

Data Index: 1301613 (Open Web Text)

Max Activating Token Index: 406

Text #7

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.3869. Min Act: -0.1700

Data Index: 4911288 (Open Web Text)

Max Activating Token Index: 528

Text #8

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.4103. Min Act: -0.1700

Data Index: 8223588 (Open Web Text)

Max Activating Token Index: 397

Text #9

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.4144. Min Act: -0.1700

Data Index: 6799377 (Open Web Text)

Max Activating Token Index: 70

Text #10

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.3496. Min Act: -0.1700

Data Index: 3135606 (Open Web Text)

Max Activating Token Index: 454

Text #11

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.3683. Min Act: -0.1700

Data Index: 8434459 (Open Web Text)

Max Activating Token Index: 557

Text #12

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.3976. Min Act: -0.1700

Data Index: 4563494 (Open Web Text)

Max Activating Token Index: 441

Text #13

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.3772. Min Act: -0.1700

Data Index: 8162468 (Open Web Text)

Max Activating Token Index: 379

Text #14

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.3716. Min Act: -0.1700

Data Index: 7940501 (Open Web Text)

Max Activating Token Index: 850

Text #15

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.3963. Min Act: -0.1700

Data Index: 6957747 (Open Web Text)

Max Activating Token Index: 680

Text #16

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.3937. Min Act: -0.1700

Data Index: 378971 (Open Web Text)

Max Activating Token Index: 407

Text #17

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.3749. Min Act: -0.1700

Data Index: 6148981 (Open Web Text)

Max Activating Token Index: 565

Text #18

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.3596. Min Act: -0.1700

Data Index: 2445788 (Open Web Text)

Max Activating Token Index: 517

Text #19

Max Range: 4.7340. Min Range: -4.7340

Max Act: 4.4030. Min Act: -0.1700

Data Index: 5407668 (Open Web Text)

Max Activating Token Index: 536