Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2485 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0467. Min Act: -0.0002

Data Index: 147689 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0445. Min Act: -0.0002

Data Index: 220738 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0404. Min Act: -0.0002

Data Index: 671063 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0349. Min Act: -0.0002

Data Index: 563374 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0389. Min Act: -0.0002

Data Index: 182337 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0395. Min Act: -0.0002

Data Index: 782834 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0367. Min Act: -0.0002

Data Index: 204057 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0384. Min Act: -0.0002

Data Index: 339396 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1181497 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1356079 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0293. Min Act: -0.0002

Data Index: 390295 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0347. Min Act: -0.0002

Data Index: 791746 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1083274 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0336. Min Act: -0.0002

Data Index: 174147 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0375. Min Act: -0.0002

Data Index: 555373 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0285. Min Act: -0.0002

Data Index: 388938 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1018604 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0342. Min Act: -0.0002

Data Index: 895086 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1552005 (Python Code)

Max Activating Token Index: 344

Text #19

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0345. Min Act: -0.0002

Data Index: 920551 (C4 (Web Text))

Max Activating Token Index: 26