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

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

Neuron 1432 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: 0.0363. Min Range: -0.0363

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1551180 (Python Code)

Max Activating Token Index: 662

Text #1

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0346. Min Act: -0.0003

Data Index: 131922 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1652466 (Python Code)

Max Activating Token Index: 390

Text #3

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0332. Min Act: -0.0003

Data Index: 1549442 (Python Code)

Max Activating Token Index: 508

Text #4

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1521510 (Python Code)

Max Activating Token Index: 862

Text #5

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1618068 (Python Code)

Max Activating Token Index: 706

Text #6

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1402798 (Python Code)

Max Activating Token Index: 969

Text #7

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1650177 (Python Code)

Max Activating Token Index: 847

Text #8

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0319. Min Act: -0.0002

Data Index: 317065 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1596269 (Python Code)

Max Activating Token Index: 719

Text #10

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1530804 (Python Code)

Max Activating Token Index: 284

Text #11

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1571529 (Python Code)

Max Activating Token Index: 804

Text #12

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0316. Min Act: -0.0003

Data Index: 20807 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1315292 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0302. Min Act: -0.0003

Data Index: 331532 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1426478 (Python Code)

Max Activating Token Index: 816

Text #16

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1432232 (Python Code)

Max Activating Token Index: 66

Text #17

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1431534 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1648005 (Python Code)

Max Activating Token Index: 41

Text #19

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0289. Min Act: -0.0003

Data Index: 990262 (C4 (Web Text))

Max Activating Token Index: 133