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

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

Neuron 784 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: 0.0361. Min Range: -0.0361

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1097486 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1025580 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0361. Min Act: -0.0002

Data Index: 845976 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0352. Min Act: -0.0003

Data Index: 257199 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0348. Min Act: -0.0004

Data Index: 460919 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0347. Min Act: -0.0003

Data Index: 646464 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1277334 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0342. Min Act: -0.0003

Data Index: 533457 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1239197 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0339. Min Act: -0.0002

Data Index: 324486 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0332. Min Act: -0.0003

Data Index: 643879 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0331. Min Act: -0.0002

Data Index: 159396 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0296. Min Act: -0.0002

Data Index: 131385 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0327. Min Act: -0.0004

Data Index: 884294 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0336. Min Act: -0.0003

Data Index: 451293 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0331. Min Act: -0.0002

Data Index: 669547 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0317. Min Act: -0.0003

Data Index: 955356 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0318. Min Act: -0.0002

Data Index: 710951 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0321. Min Act: -0.0004

Data Index: 216136 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0313. Min Act: -0.0002

Data Index: 472745 (C4 (Web Text))

Max Activating Token Index: 969