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

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

Neuron 1403 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.5231. Min Act: -0.0000

Data Index: 90438 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4943. Min Act: -0.0000

Data Index: 1213327 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4246. Min Act: -0.0000

Data Index: 610746 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4335. Min Act: -0.0000

Data Index: 898882 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1017197 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4453. Min Act: -0.0000

Data Index: 661486 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.4023. Min Act: -0.0000

Data Index: 254004 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.3425. Min Act: -0.0000

Data Index: 171585 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.3655. Min Act: -0.0000

Data Index: 25988 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.3470. Min Act: -0.0000

Data Index: 150960 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.3419. Min Act: -0.0000

Data Index: 263765 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.3439. Min Act: -0.0000

Data Index: 358023 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.3396. Min Act: -0.0000

Data Index: 962732 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1066498 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.3321. Min Act: -0.0000

Data Index: 253218 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.3156. Min Act: -0.0000

Data Index: 223986 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1611441 (Python Code)

Max Activating Token Index: 254

Text #17

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1314940 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.2794. Min Act: -0.0000

Data Index: 829658 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.5231. Min Range: -0.5231

Max Act: 0.2638. Min Act: -0.0000

Data Index: 865915 (C4 (Web Text))

Max Activating Token Index: 562