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

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

Neuron 15 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0406. Min Act: -0.0003

Data Index: 663037 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0384. Min Act: -0.0003

Data Index: 996239 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1194284 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1076752 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1316450 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0349. Min Act: -0.0002

Data Index: 736173 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1449641 (Python Code)

Max Activating Token Index: 567

Text #7

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1154620 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1337457 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1150051 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1590097 (Python Code)

Max Activating Token Index: 296

Text #11

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0319. Min Act: -0.0003

Data Index: 434638 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1238309 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1571072 (Python Code)

Max Activating Token Index: 731

Text #14

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0308. Min Act: -0.0003

Data Index: 615452 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1403989 (Python Code)

Max Activating Token Index: 812

Text #16

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0308. Min Act: -0.0003

Data Index: 351708 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0312. Min Act: -0.0003

Data Index: 974436 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0311. Min Act: -0.0003

Data Index: 216524 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1519569 (Python Code)

Max Activating Token Index: 392