Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1691 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0332. Min Act: -0.0003

Data Index: 28313 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0238. Min Act: -0.0003

Data Index: 666951 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0219. Min Act: -0.0003

Data Index: 124707 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0215. Min Act: -0.0002

Data Index: 305346 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0205. Min Act: -0.0003

Data Index: 165539 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1326778 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0200. Min Act: -0.0003

Data Index: 1111946 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0197. Min Act: -0.0003

Data Index: 170280 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0199. Min Act: -0.0003

Data Index: 238319 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0194. Min Act: -0.0004

Data Index: 578823 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1329487 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0191. Min Act: -0.0003

Data Index: 432461 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0199. Min Act: -0.0003

Data Index: 161369 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0192. Min Act: -0.0003

Data Index: 910295 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0191. Min Act: -0.0003

Data Index: 1136464 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0191. Min Act: -0.0003

Data Index: 669046 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0190. Min Act: -0.0003

Data Index: 107586 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0186. Min Act: -0.0003

Data Index: 281304 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1285307 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1326211 (C4 (Web Text))

Max Activating Token Index: 862