Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1170 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0380. Min Act: -0.0003

Data Index: 746842 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0316. Min Act: -0.0003

Data Index: 420744 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0326. Min Act: -0.0003

Data Index: 727616 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1014926 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1163533 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1996 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0290. Min Act: -0.0003

Data Index: 481523 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0294. Min Act: -0.0003

Data Index: 989862 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0286. Min Act: -0.0003

Data Index: 542227 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1096311 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0276. Min Act: -0.0003

Data Index: 796421 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0291. Min Act: -0.0003

Data Index: 745516 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0287. Min Act: -0.0003

Data Index: 406718 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0285. Min Act: -0.0003

Data Index: 810118 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0285. Min Act: -0.0004

Data Index: 338235 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1161070 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0279. Min Act: -0.0003

Data Index: 49630 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0275. Min Act: -0.0003

Data Index: 508846 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0275. Min Act: -0.0003

Data Index: 933698 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1052944 (C4 (Web Text))

Max Activating Token Index: 443