Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 108 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.2991. Min Act: -0.0000

Data Index: 535912 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.4363. Min Act: -0.0000

Data Index: 369112 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.2333. Min Act: -0.0000

Data Index: 1266601 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.1306. Min Act: -0.0000

Data Index: 492809 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.1202. Min Act: -0.0000

Data Index: 129015 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.2185. Min Act: -0.0000

Data Index: 44783 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.0738. Min Act: -0.0000

Data Index: 851113 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.0839. Min Act: -0.0000

Data Index: 817177 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.0695. Min Act: -0.0000

Data Index: 1028471 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.0640. Min Act: -0.0000

Data Index: 861953 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.0566. Min Act: -0.0000

Data Index: 429729 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.0538. Min Act: -0.0000

Data Index: 518653 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.0482. Min Act: -0.0000

Data Index: 455976 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 2.4363. Min Range: -2.4363

Max Act: 1.9342. Min Act: -0.0000

Data Index: 1125367 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 2.4363. Min Range: -2.4363

Max Act: 1.9433. Min Act: -0.0000

Data Index: 10042 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.1465. Min Act: -0.0000

Data Index: 348043 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.0323. Min Act: -0.0000

Data Index: 783516 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 2.4363. Min Range: -2.4363

Max Act: 1.9940. Min Act: -0.0000

Data Index: 614596 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 2.4363. Min Range: -2.4363

Max Act: 2.0177. Min Act: -0.0000

Data Index: 1341229 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 2.4363. Min Range: -2.4363

Max Act: 1.8909. Min Act: -0.0000

Data Index: 1259032 (C4 (Web Text))

Max Activating Token Index: 78