Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1605 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0401. Min Act: -0.0003

Data Index: 634396 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1031050 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0330. Min Act: -0.0003

Data Index: 510976 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0281. Min Act: -0.0003

Data Index: 56176 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1098319 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0231. Min Act: -0.0002

Data Index: 648002 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0225. Min Act: -0.0003

Data Index: 661744 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0226. Min Act: -0.0003

Data Index: 575066 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0230. Min Act: -0.0002

Data Index: 866671 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0223. Min Act: -0.0003

Data Index: 348624 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0245. Min Act: -0.0003

Data Index: 281258 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1163935 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0214. Min Act: -0.0003

Data Index: 1296029 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0212. Min Act: -0.0003

Data Index: 169679 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0209. Min Act: -0.0002

Data Index: 662164 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0211. Min Act: -0.0003

Data Index: 435776 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0207. Min Act: -0.0002

Data Index: 18577 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1261136 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0210. Min Act: -0.0003

Data Index: 317411 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1240927 (C4 (Web Text))

Max Activating Token Index: 150