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

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

Neuron 1697 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: 0.0316. Min Range: -0.0316

Max Act: 0.0316. Min Act: -0.0006

Data Index: 935655 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0282. Min Act: -0.0006

Data Index: 1096671 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0267. Min Act: -0.0006

Data Index: 1334994 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0275. Min Act: -0.0006

Data Index: 451758 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0255. Min Act: -0.0006

Data Index: 157306 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1098609 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0277. Min Act: -0.0006

Data Index: 651759 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0259. Min Act: -0.0006

Data Index: 14105 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0278. Min Act: -0.0006

Data Index: 615738 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0238. Min Act: -0.0006

Data Index: 361866 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0256. Min Act: -0.0006

Data Index: 152591 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1184060 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0247. Min Act: -0.0006

Data Index: 533732 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0247. Min Act: -0.0006

Data Index: 1135769 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0260. Min Act: -0.0006

Data Index: 66521 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0248. Min Act: -0.0006

Data Index: 752252 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0230. Min Act: -0.0006

Data Index: 39050 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0246. Min Act: -0.0006

Data Index: 6007 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0245. Min Act: -0.0006

Data Index: 443077 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1053836 (C4 (Web Text))

Max Activating Token Index: 549