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

Dataset: Open Web Text

Neuron 1683 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: 4.1341. Min Range: -4.1341

Max Act: 4.1139. Min Act: -0.1700

Data Index: 7427975 (Open Web Text)

Max Activating Token Index: 949

Text #1

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.1341. Min Act: -0.1700

Data Index: 7138585 (Open Web Text)

Max Activating Token Index: 654

Text #2

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0856. Min Act: -0.1700

Data Index: 8787368 (Open Web Text)

Max Activating Token Index: 914

Text #3

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0876. Min Act: -0.1700

Data Index: 6289161 (Open Web Text)

Max Activating Token Index: 578

Text #4

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0728. Min Act: -0.1700

Data Index: 613708 (Open Web Text)

Max Activating Token Index: 919

Text #5

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0759. Min Act: -0.1700

Data Index: 3194107 (Open Web Text)

Max Activating Token Index: 584

Text #6

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0846. Min Act: -0.1700

Data Index: 6424582 (Open Web Text)

Max Activating Token Index: 931

Text #7

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0567. Min Act: -0.1700

Data Index: 591152 (Open Web Text)

Max Activating Token Index: 324

Text #8

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0290. Min Act: -0.1700

Data Index: 10422 (Open Web Text)

Max Activating Token Index: 442

Text #9

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0403. Min Act: -0.1700

Data Index: 3967450 (Open Web Text)

Max Activating Token Index: 221

Text #10

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0317. Min Act: -0.1700

Data Index: 7861653 (Open Web Text)

Max Activating Token Index: 988

Text #11

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0209. Min Act: -0.1700

Data Index: 3346920 (Open Web Text)

Max Activating Token Index: 959

Text #12

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0363. Min Act: -0.1700

Data Index: 6487242 (Open Web Text)

Max Activating Token Index: 945

Text #13

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0340. Min Act: -0.1700

Data Index: 1812589 (Open Web Text)

Max Activating Token Index: 494

Text #14

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0181. Min Act: -0.1700

Data Index: 771135 (Open Web Text)

Max Activating Token Index: 1012

Text #15

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0155. Min Act: -0.1700

Data Index: 6045449 (Open Web Text)

Max Activating Token Index: 464

Text #16

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0260. Min Act: -0.1700

Data Index: 1564345 (Open Web Text)

Max Activating Token Index: 521

Text #17

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0205. Min Act: -0.1700

Data Index: 4923756 (Open Web Text)

Max Activating Token Index: 519

Text #18

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0397. Min Act: -0.1700

Data Index: 62806 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 4.1341. Min Range: -4.1341

Max Act: 4.0132. Min Act: -0.1700

Data Index: 4542897 (Open Web Text)

Max Activating Token Index: 434