Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 715 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0405. Min Act: -0.0006

Data Index: 1326457 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0403. Min Act: -0.0006

Data Index: 920058 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0383. Min Act: -0.0006

Data Index: 1169329 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0381. Min Act: -0.0006

Data Index: 381978 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0378. Min Act: -0.0006

Data Index: 646328 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0390. Min Act: -0.0006

Data Index: 1115462 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0352. Min Act: -0.0006

Data Index: 945374 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0375. Min Act: -0.0006

Data Index: 734123 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0358. Min Act: -0.0006

Data Index: 670712 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0324. Min Act: -0.0006

Data Index: 1303217 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0350. Min Act: -0.0006

Data Index: 1103572 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0371. Min Act: -0.0006

Data Index: 254978 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0348. Min Act: -0.0006

Data Index: 1033688 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0339. Min Act: -0.0006

Data Index: 1195412 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0345. Min Act: -0.0006

Data Index: 727365 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0322. Min Act: -0.0006

Data Index: 57935 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0289. Min Act: -0.0006

Data Index: 1086950 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0339. Min Act: -0.0006

Data Index: 465582 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0328. Min Act: -0.0006

Data Index: 1612711 (Python Code)

Max Activating Token Index: 557

Text #19

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0320. Min Act: -0.0006

Data Index: 280992 (C4 (Web Text))

Max Activating Token Index: 692