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

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

Neuron 1806 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: 0.0242. Min Range: -0.0242

Max Act: 0.0242. Min Act: -0.0006

Data Index: 860826 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0228. Min Act: -0.0006

Data Index: 34518 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0232. Min Act: -0.0006

Data Index: 65878 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0229. Min Act: -0.0006

Data Index: 97967 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0224. Min Act: -0.0006

Data Index: 445114 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0227. Min Act: -0.0006

Data Index: 862394 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0228. Min Act: -0.0006

Data Index: 541378 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1186605 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1226592 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0219. Min Act: -0.0006

Data Index: 342925 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0224. Min Act: -0.0006

Data Index: 960416 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0229. Min Act: -0.0006

Data Index: 424518 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0218. Min Act: -0.0006

Data Index: 150289 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0217. Min Act: -0.0006

Data Index: 708308 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0227. Min Act: -0.0006

Data Index: 390850 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0222. Min Act: -0.0006

Data Index: 139197 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0217. Min Act: -0.0006

Data Index: 589879 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0222. Min Act: -0.0006

Data Index: 769840 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0235. Min Act: -0.0006

Data Index: 878072 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1214113 (C4 (Web Text))

Max Activating Token Index: 90