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

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

Neuron 1758 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0276. Min Act: -0.0006

Data Index: 719384 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0247. Min Act: -0.0006

Data Index: 878522 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0255. Min Act: -0.0006

Data Index: 684986 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1412655 (Python Code)

Max Activating Token Index: 992

Text #4

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0233. Min Act: -0.0006

Data Index: 362454 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0237. Min Act: -0.0006

Data Index: 354583 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1574663 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0232. Min Act: -0.0006

Data Index: 854061 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0227. Min Act: -0.0006

Data Index: 689931 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1055826 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0226. Min Act: -0.0006

Data Index: 726030 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1391895 (Python Code)

Max Activating Token Index: 114

Text #12

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1553463 (Python Code)

Max Activating Token Index: 601

Text #13

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0220. Min Act: -0.0006

Data Index: 509895 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1525983 (Python Code)

Max Activating Token Index: 613

Text #15

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0228. Min Act: -0.0006

Data Index: 760204 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0227. Min Act: -0.0006

Data Index: 824606 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1608286 (Python Code)

Max Activating Token Index: 796

Text #18

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0221. Min Act: -0.0006

Data Index: 829084 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0216. Min Act: -0.0006

Data Index: 496263 (C4 (Web Text))

Max Activating Token Index: 624