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

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

Neuron 2006 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0305. Min Act: -0.0006

Data Index: 61185 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0319. Min Act: -0.0005

Data Index: 1582770 (Python Code)

Max Activating Token Index: 250

Text #2

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0277. Min Act: -0.0006

Data Index: 407448 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0280. Min Act: -0.0006

Data Index: 575013 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0282. Min Act: -0.0006

Data Index: 1410724 (Python Code)

Max Activating Token Index: 974

Text #5

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0274. Min Act: -0.0006

Data Index: 829756 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0263. Min Act: -0.0006

Data Index: 309660 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0266. Min Act: -0.0006

Data Index: 326211 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0267. Min Act: -0.0006

Data Index: 216331 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0266. Min Act: -0.0006

Data Index: 1100153 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0263. Min Act: -0.0006

Data Index: 808684 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0262. Min Act: -0.0006

Data Index: 382278 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0255. Min Act: -0.0006

Data Index: 477440 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0260. Min Act: -0.0006

Data Index: 641288 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0260. Min Act: -0.0006

Data Index: 97966 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0259. Min Act: -0.0006

Data Index: 846338 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0250. Min Act: -0.0006

Data Index: 232626 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0258. Min Act: -0.0006

Data Index: 360729 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0262. Min Act: -0.0006

Data Index: 699803 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1161823 (C4 (Web Text))

Max Activating Token Index: 153