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

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

Neuron 1491 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: 0.0318. Min Range: -0.0318

Max Act: 0.0318. Min Act: -0.0006

Data Index: 1074287 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0285. Min Act: -0.0006

Data Index: 267573 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0257. Min Act: -0.0006

Data Index: 682381 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0246. Min Act: -0.0006

Data Index: 865267 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0236. Min Act: -0.0006

Data Index: 118026 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1318093 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1044672 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0231. Min Act: -0.0006

Data Index: 553067 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1349343 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0235. Min Act: -0.0006

Data Index: 783596 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0208. Min Act: -0.0006

Data Index: 551965 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0228. Min Act: -0.0006

Data Index: 580542 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0232. Min Act: -0.0006

Data Index: 302114 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0225. Min Act: -0.0006

Data Index: 47637 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1136497 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0231. Min Act: -0.0006

Data Index: 457897 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0220. Min Act: -0.0006

Data Index: 762302 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0230. Min Act: -0.0006

Data Index: 992321 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0224. Min Act: -0.0006

Data Index: 827405 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1281192 (C4 (Web Text))

Max Activating Token Index: 210