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

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

Neuron 2994 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1295150 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1281367 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0345. Min Act: -0.0002

Data Index: 828511 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0315. Min Act: -0.0002

Data Index: 253751 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0320. Min Act: -0.0002

Data Index: 570733 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0299. Min Act: -0.0002

Data Index: 102860 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0307. Min Act: -0.0002

Data Index: 16506 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1096898 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1156055 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0303. Min Act: -0.0002

Data Index: 225817 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0309. Min Act: -0.0002

Data Index: 21703 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1165005 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0296. Min Act: -0.0002

Data Index: 485921 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0295. Min Act: -0.0002

Data Index: 296489 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0292. Min Act: -0.0002

Data Index: 258688 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0285. Min Act: -0.0002

Data Index: 921693 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1260964 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0285. Min Act: -0.0002

Data Index: 94027 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0277. Min Act: -0.0002

Data Index: 386731 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0264. Min Act: -0.0002

Data Index: 3972 (C4 (Web Text))

Max Activating Token Index: 257