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

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

Neuron 760 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: 0.0259. Min Range: -0.0259

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1143034 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0239. Min Act: -0.0006

Data Index: 134861 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0225. Min Act: -0.0006

Data Index: 453929 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1167362 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0223. Min Act: -0.0006

Data Index: 265343 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0222. Min Act: -0.0006

Data Index: 702603 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1267109 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0210. Min Act: -0.0006

Data Index: 104182 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0208. Min Act: -0.0006

Data Index: 455460 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1053022 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0204. Min Act: -0.0006

Data Index: 626481 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0204. Min Act: -0.0006

Data Index: 762645 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0207. Min Act: -0.0006

Data Index: 142075 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1210888 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0204. Min Act: -0.0006

Data Index: 977251 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1231707 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1079623 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0199. Min Act: -0.0006

Data Index: 561850 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0190. Min Act: -0.0006

Data Index: 787654 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0194. Min Act: -0.0006

Data Index: 137945 (C4 (Web Text))

Max Activating Token Index: 263