Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4168 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0315. Min Act: -0.0001

Data Index: 615454 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0307. Min Act: -0.0001

Data Index: 498904 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1166191 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0280. Min Act: -0.0001

Data Index: 575601 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0259. Min Act: -0.0001

Data Index: 42057 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0266. Min Act: -0.0001

Data Index: 650303 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0258. Min Act: -0.0001

Data Index: 268387 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0270. Min Act: -0.0001

Data Index: 784708 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0234. Min Act: -0.0001

Data Index: 281181 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0240. Min Act: -0.0001

Data Index: 863439 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0233. Min Act: -0.0001

Data Index: 725436 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0244. Min Act: -0.0001

Data Index: 66661 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0224. Min Act: -0.0001

Data Index: 736355 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0238. Min Act: -0.0001

Data Index: 1228802 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0210. Min Act: -0.0001

Data Index: 574276 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0234. Min Act: -0.0001

Data Index: 1240734 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0217. Min Act: -0.0001

Data Index: 1374089 (Python Code)

Max Activating Token Index: 192

Text #17

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0237. Min Act: -0.0001

Data Index: 401442 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0222. Min Act: -0.0001

Data Index: 176177 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0226. Min Act: -0.0001

Data Index: 540662 (C4 (Web Text))

Max Activating Token Index: 393