Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4032 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.8486. Min Act: -0.0001

Data Index: 506593 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.7582. Min Act: -0.0000

Data Index: 1315654 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1245234 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.6374. Min Act: -0.0001

Data Index: 238198 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1164395 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5841. Min Act: -0.0000

Data Index: 311498 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5757. Min Act: -0.0000

Data Index: 292413 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5640. Min Act: -0.0000

Data Index: 535760 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5689. Min Act: -0.0000

Data Index: 268731 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5310. Min Act: -0.0001

Data Index: 338440 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5290. Min Act: -0.0000

Data Index: 1248076 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.4872. Min Act: -0.0001

Data Index: 330029 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5192. Min Act: -0.0001

Data Index: 990080 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5173. Min Act: -0.0000

Data Index: 728244 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.4902. Min Act: -0.0001

Data Index: 408905 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5257. Min Act: -0.0001

Data Index: 496947 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.4841. Min Act: -0.0001

Data Index: 737304 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1252672 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.4871. Min Act: -0.0001

Data Index: 606053 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.4707. Min Act: -0.0001

Data Index: 730348 (C4 (Web Text))

Max Activating Token Index: 257