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

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

Neuron 1275 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: 0.0323. Min Range: -0.0323

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1179071 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0311. Min Act: -0.0004

Data Index: 1148810 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0298. Min Act: -0.0003

Data Index: 632097 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0303. Min Act: -0.0002

Data Index: 301592 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0294. Min Act: -0.0004

Data Index: 923215 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1333202 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0285. Min Act: -0.0003

Data Index: 384135 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0293. Min Act: -0.0003

Data Index: 606535 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0276. Min Act: -0.0003

Data Index: 671362 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0271. Min Act: -0.0004

Data Index: 59355 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0266. Min Act: -0.0003

Data Index: 606005 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0264. Min Act: -0.0003

Data Index: 60119 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0255. Min Act: -0.0003

Data Index: 743424 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0257. Min Act: -0.0003

Data Index: 771285 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0260. Min Act: -0.0004

Data Index: 890495 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0251. Min Act: -0.0004

Data Index: 414011 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1035053 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1246893 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1348978 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0252. Min Act: -0.0003

Data Index: 968143 (C4 (Web Text))

Max Activating Token Index: 536