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

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

Neuron 3806 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: 0.0407. Min Range: -0.0407

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1367902 (Python Code)

Max Activating Token Index: 497

Text #1

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1647543 (Python Code)

Max Activating Token Index: 324

Text #2

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1456376 (Python Code)

Max Activating Token Index: 301

Text #3

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0363. Min Act: -0.0004

Data Index: 2667 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1614678 (Python Code)

Max Activating Token Index: 42

Text #5

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1509186 (Python Code)

Max Activating Token Index: 306

Text #6

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1562412 (Python Code)

Max Activating Token Index: 59

Text #7

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1450961 (Python Code)

Max Activating Token Index: 866

Text #8

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1514625 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1609054 (Python Code)

Max Activating Token Index: 741

Text #10

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1547387 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0289. Min Act: -0.0003

Data Index: 1444138 (Python Code)

Max Activating Token Index: 912

Text #12

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1451356 (Python Code)

Max Activating Token Index: 382

Text #13

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1297231 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1549055 (Python Code)

Max Activating Token Index: 467

Text #15

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1656158 (Python Code)

Max Activating Token Index: 170

Text #16

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1419432 (Python Code)

Max Activating Token Index: 605

Text #17

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0332. Min Act: -0.0004

Data Index: 1481485 (Python Code)

Max Activating Token Index: 815

Text #18

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1463571 (Python Code)

Max Activating Token Index: 335

Text #19

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1641012 (Python Code)

Max Activating Token Index: 661