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

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

Neuron 3651 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1475405 (Python Code)

Max Activating Token Index: 51

Text #1

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1057374 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2787. Min Act: -0.0000

Data Index: 602957 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2448. Min Act: -0.0000

Data Index: 673648 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1182965 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2296. Min Act: -0.0000

Data Index: 324373 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2273. Min Act: -0.0000

Data Index: 419305 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2237. Min Act: -0.0000

Data Index: 801481 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2231. Min Act: -0.0000

Data Index: 436462 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1141326 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2158. Min Act: -0.0000

Data Index: 856769 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2048. Min Act: -0.0000

Data Index: 592828 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2240. Min Act: -0.0000

Data Index: 806128 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.1996. Min Act: -0.0000

Data Index: 308779 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.1977. Min Act: -0.0000

Data Index: 917011 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2014. Min Act: -0.0000

Data Index: 827780 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2041. Min Act: -0.0000

Data Index: 1254953 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.1776. Min Act: -0.0000

Data Index: 549923 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.1832. Min Act: -0.0000

Data Index: 772818 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.1956. Min Act: -0.0000

Data Index: 575703 (C4 (Web Text))

Max Activating Token Index: 404