Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3689 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1458480 (Python Code)

Max Activating Token Index: 186

Text #1

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0370. Min Act: -0.0003

Data Index: 539971 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0376. Min Act: -0.0004

Data Index: 1102553 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0346. Min Act: -0.0003

Data Index: 80583 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1132748 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0367. Min Act: -0.0003

Data Index: 684841 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0352. Min Act: -0.0003

Data Index: 456444 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0343. Min Act: -0.0003

Data Index: 654096 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0295. Min Act: -0.0003

Data Index: 446936 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0341. Min Act: -0.0003

Data Index: 829509 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0319. Min Act: -0.0003

Data Index: 246016 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0332. Min Act: -0.0003

Data Index: 601055 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0333. Min Act: -0.0003

Data Index: 948471 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1417633 (Python Code)

Max Activating Token Index: 234

Text #14

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0323. Min Act: -0.0003

Data Index: 433767 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0337. Min Act: -0.0003

Data Index: 107195 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0341. Min Act: -0.0003

Data Index: 878261 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0342. Min Act: -0.0003

Data Index: 772863 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0333. Min Act: -0.0003

Data Index: 187152 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0330. Min Act: -0.0004

Data Index: 1228221 (C4 (Web Text))

Max Activating Token Index: 885