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

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

Neuron 1128 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1485435 (Python Code)

Max Activating Token Index: 46

Text #1

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0357. Min Act: -0.0001

Data Index: 566248 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0299. Min Act: -0.0001

Data Index: 418085 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0284. Min Act: -0.0002

Data Index: 34406 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0315. Min Act: -0.0002

Data Index: 852745 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0304. Min Act: -0.0001

Data Index: 785607 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0295. Min Act: -0.0001

Data Index: 1616152 (Python Code)

Max Activating Token Index: 72

Text #7

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0290. Min Act: -0.0002

Data Index: 800325 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0289. Min Act: -0.0002

Data Index: 799210 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0308. Min Act: -0.0002

Data Index: 371199 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0297. Min Act: -0.0002

Data Index: 915222 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0291. Min Act: -0.0001

Data Index: 1349149 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0288. Min Act: -0.0002

Data Index: 835758 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0308. Min Act: -0.0001

Data Index: 1529383 (Python Code)

Max Activating Token Index: 392

Text #14

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0274. Min Act: -0.0002

Data Index: 401695 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0279. Min Act: -0.0002

Data Index: 549988 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0291. Min Act: -0.0001

Data Index: 653514 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1146222 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0256. Min Act: -0.0002

Data Index: 195530 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0256. Min Act: -0.0002

Data Index: 721364 (C4 (Web Text))

Max Activating Token Index: 857