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

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

Neuron 3070 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: 0.0427. Min Range: -0.0427

Max Act: 0.0427. Min Act: -0.0003

Data Index: 27671 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0344. Min Act: -0.0003

Data Index: 985290 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0355. Min Act: -0.0003

Data Index: 306442 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1153837 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1007296 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0329. Min Act: -0.0003

Data Index: 627941 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0314. Min Act: -0.0003

Data Index: 633759 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0318. Min Act: -0.0003

Data Index: 835505 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0330. Min Act: -0.0003

Data Index: 577845 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0312. Min Act: -0.0003

Data Index: 1239306 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1296733 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1024611 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0329. Min Act: -0.0003

Data Index: 121005 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0292. Min Act: -0.0003

Data Index: 894169 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0298. Min Act: -0.0003

Data Index: 908029 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1206460 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0295. Min Act: -0.0003

Data Index: 209087 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0288. Min Act: -0.0003

Data Index: 686238 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0292. Min Act: -0.0003

Data Index: 648918 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1012454 (C4 (Web Text))

Max Activating Token Index: 504