Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1980 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0634. Min Act: -0.0006

Data Index: 1388406 (Python Code)

Max Activating Token Index: 852

Text #1

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0354. Min Act: -0.0006

Data Index: 327294 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0280. Min Act: -0.0006

Data Index: 979512 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0255. Min Act: -0.0006

Data Index: 399663 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1155971 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0252. Min Act: -0.0006

Data Index: 1121971 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1382997 (Python Code)

Max Activating Token Index: 971

Text #7

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0251. Min Act: -0.0006

Data Index: 156616 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0237. Min Act: -0.0006

Data Index: 542140 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0224. Min Act: -0.0006

Data Index: 854222 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0234. Min Act: -0.0006

Data Index: 584323 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0237. Min Act: -0.0006

Data Index: 727253 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1097501 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0233. Min Act: -0.0006

Data Index: 216555 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0228. Min Act: -0.0005

Data Index: 1626291 (Python Code)

Max Activating Token Index: 478

Text #15

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0233. Min Act: -0.0005

Data Index: 1550099 (Python Code)

Max Activating Token Index: 424

Text #16

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0220. Min Act: -0.0006

Data Index: 1015632 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0225. Min Act: -0.0006

Data Index: 438939 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1540254 (Python Code)

Max Activating Token Index: 468

Text #19

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0228. Min Act: -0.0006

Data Index: 981231 (C4 (Web Text))

Max Activating Token Index: 645