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

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

Neuron 1216 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0323. Min Act: -0.0004

Data Index: 895875 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0311. Min Act: -0.0003

Data Index: 434427 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0293. Min Act: -0.0003

Data Index: 269163 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0310. Min Act: -0.0003

Data Index: 270286 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0261. Min Act: -0.0004

Data Index: 665612 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1305836 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0279. Min Act: -0.0003

Data Index: 596382 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0249. Min Act: -0.0003

Data Index: 911560 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0222. Min Act: -0.0003

Data Index: 16256 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0252. Min Act: -0.0003

Data Index: 355924 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0300. Min Act: -0.0003

Data Index: 862854 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1213617 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0226. Min Act: -0.0003

Data Index: 376053 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1025542 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0272. Min Act: -0.0003

Data Index: 173989 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0268. Min Act: -0.0003

Data Index: 117614 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0285. Min Act: -0.0003

Data Index: 386928 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0277. Min Act: -0.0003

Data Index: 630089 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0288. Min Act: -0.0003

Data Index: 313660 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1360 (C4 (Web Text))

Max Activating Token Index: 531