Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 254 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0334. Min Act: -0.0006

Data Index: 46531 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0331. Min Act: -0.0006

Data Index: 566195 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0323. Min Act: -0.0006

Data Index: 236442 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0321. Min Act: -0.0006

Data Index: 1094305 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0315. Min Act: -0.0006

Data Index: 58350 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0305. Min Act: -0.0006

Data Index: 379148 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0288. Min Act: -0.0006

Data Index: 935538 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0299. Min Act: -0.0006

Data Index: 898126 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0302. Min Act: -0.0006

Data Index: 1020406 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0302. Min Act: -0.0006

Data Index: 591597 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0289. Min Act: -0.0006

Data Index: 199639 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0300. Min Act: -0.0006

Data Index: 171626 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0299. Min Act: -0.0006

Data Index: 926165 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0303. Min Act: -0.0006

Data Index: 578432 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0290. Min Act: -0.0006

Data Index: 95736 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0293. Min Act: -0.0006

Data Index: 77556 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0307. Min Act: -0.0006

Data Index: 1355411 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0293. Min Act: -0.0006

Data Index: 1292983 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0306. Min Act: -0.0006

Data Index: 636001 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0286. Min Act: -0.0006

Data Index: 1020043 (C4 (Web Text))

Max Activating Token Index: 783