Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 832 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0282. Min Act: -0.0006

Data Index: 311188 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0006

Data Index: 700994 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0301. Min Act: -0.0006

Data Index: 913947 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0292. Min Act: -0.0006

Data Index: 2560 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0304. Min Act: -0.0006

Data Index: 120164 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0279. Min Act: -0.0006

Data Index: 863907 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0280. Min Act: -0.0006

Data Index: 180913 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0272. Min Act: -0.0006

Data Index: 1045831 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0270. Min Act: -0.0006

Data Index: 680423 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1205237 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1060096 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1100509 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0226. Min Act: -0.0006

Data Index: 172574 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0261. Min Act: -0.0006

Data Index: 262046 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0251. Min Act: -0.0006

Data Index: 443569 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1157991 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0253. Min Act: -0.0006

Data Index: 317606 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0239. Min Act: -0.0006

Data Index: 588386 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0224. Min Act: -0.0006

Data Index: 441520 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1070831 (C4 (Web Text))

Max Activating Token Index: 594