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

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

Neuron 544 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0399. Min Act: -0.0006

Data Index: 101604 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0378. Min Act: -0.0006

Data Index: 597519 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0357. Min Act: -0.0005

Data Index: 1166356 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0342. Min Act: -0.0005

Data Index: 1318400 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0347. Min Act: -0.0005

Data Index: 476971 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0336. Min Act: -0.0006

Data Index: 1024171 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0335. Min Act: -0.0006

Data Index: 614022 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0328. Min Act: -0.0005

Data Index: 695655 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0326. Min Act: -0.0005

Data Index: 340767 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0314. Min Act: -0.0005

Data Index: 635607 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0322. Min Act: -0.0005

Data Index: 37562 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0322. Min Act: -0.0005

Data Index: 842659 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0308. Min Act: -0.0005

Data Index: 1087599 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0313. Min Act: -0.0006

Data Index: 1099717 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0305. Min Act: -0.0005

Data Index: 243730 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0309. Min Act: -0.0005

Data Index: 478697 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0307. Min Act: -0.0005

Data Index: 1003052 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0302. Min Act: -0.0006

Data Index: 1062154 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0302. Min Act: -0.0005

Data Index: 220380 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0301. Min Act: -0.0006

Data Index: 1102504 (C4 (Web Text))

Max Activating Token Index: 757