Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 901 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0388. Min Act: -0.0002

Data Index: 749999 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0381. Min Act: -0.0003

Data Index: 835020 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0363. Min Act: -0.0003

Data Index: 319689 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0349. Min Act: -0.0003

Data Index: 205076 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1503448 (Python Code)

Max Activating Token Index: 28

Text #5

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0335. Min Act: -0.0003

Data Index: 607389 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0333. Min Act: -0.0003

Data Index: 227643 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0336. Min Act: -0.0003

Data Index: 240180 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1111053 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0331. Min Act: -0.0003

Data Index: 93243 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0328. Min Act: -0.0003

Data Index: 835526 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1331432 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1370695 (Python Code)

Max Activating Token Index: 156

Text #13

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1225005 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0315. Min Act: -0.0003

Data Index: 720031 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0315. Min Act: -0.0003

Data Index: 776750 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0305. Min Act: -0.0003

Data Index: 919784 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0307. Min Act: -0.0004

Data Index: 116191 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1172003 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0317. Min Act: -0.0002

Data Index: 403455 (C4 (Web Text))

Max Activating Token Index: 920