Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 326 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0404. Min Act: -0.0003

Data Index: 165287 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0398. Min Act: -0.0003

Data Index: 903741 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0362. Min Act: -0.0003

Data Index: 391380 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0349. Min Act: -0.0003

Data Index: 84320 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0369. Min Act: -0.0003

Data Index: 1277923 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0368. Min Act: -0.0003

Data Index: 305550 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1238268 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1268631 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0358. Min Act: -0.0002

Data Index: 203819 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0339. Min Act: -0.0002

Data Index: 75678 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0340. Min Act: -0.0004

Data Index: 910964 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0347. Min Act: -0.0002

Data Index: 275020 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1138516 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1333096 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0344. Min Act: -0.0003

Data Index: 527073 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1326777 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0330. Min Act: -0.0003

Data Index: 941458 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0332. Min Act: -0.0003

Data Index: 566814 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0339. Min Act: -0.0002

Data Index: 962109 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1077388 (C4 (Web Text))

Max Activating Token Index: 573