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

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

Neuron 1049 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0006

Data Index: 569334 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0340. Min Act: -0.0006

Data Index: 1022952 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0323. Min Act: -0.0005

Data Index: 745862 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0321. Min Act: -0.0006

Data Index: 360167 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0334. Min Act: -0.0006

Data Index: 401366 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0334. Min Act: -0.0006

Data Index: 604688 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0283. Min Act: -0.0006

Data Index: 730450 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0343. Min Act: -0.0006

Data Index: 181335 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0324. Min Act: -0.0006

Data Index: 223725 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0303. Min Act: -0.0006

Data Index: 992723 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0308. Min Act: -0.0006

Data Index: 803617 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0305. Min Act: -0.0006

Data Index: 230838 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0318. Min Act: -0.0006

Data Index: 1354480 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0297. Min Act: -0.0006

Data Index: 905892 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0306. Min Act: -0.0006

Data Index: 1327794 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0280. Min Act: -0.0006

Data Index: 1210284 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0266. Min Act: -0.0006

Data Index: 207859 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0301. Min Act: -0.0006

Data Index: 609754 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0306. Min Act: -0.0006

Data Index: 1020458 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0306. Min Act: -0.0006

Data Index: 4691 (C4 (Web Text))

Max Activating Token Index: 111