Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3340 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0524. Min Range: -1.0524

Max Act: 1.0524. Min Act: -0.0000

Data Index: 580377 (The Pile)

Max Activating Token Index: 259

Text #1

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1877942 (The Pile)

Max Activating Token Index: 751

Text #2

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.9907. Min Act: -0.0000

Data Index: 201181 (The Pile)

Max Activating Token Index: 874

Text #3

Max Range: 1.0524. Min Range: -1.0524

Max Act: 1.0434. Min Act: -0.0000

Data Index: 362450 (The Pile)

Max Activating Token Index: 184

Text #4

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.9133. Min Act: -0.0000

Data Index: 1805170 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.9386. Min Act: -0.0000

Data Index: 357385 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1121564 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.9772. Min Act: -0.0000

Data Index: 236668 (The Pile)

Max Activating Token Index: 646

Text #8

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1316388 (The Pile)

Max Activating Token Index: 260

Text #9

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1907598 (The Pile)

Max Activating Token Index: 480

Text #10

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.8313. Min Act: -0.0000

Data Index: 577221 (The Pile)

Max Activating Token Index: 104

Text #11

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.9084. Min Act: -0.0000

Data Index: 621669 (The Pile)

Max Activating Token Index: 221

Text #12

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7889. Min Act: -0.0000

Data Index: 868832 (The Pile)

Max Activating Token Index: 913

Text #13

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1507257 (The Pile)

Max Activating Token Index: 758

Text #14

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.8364. Min Act: -0.0000

Data Index: 381398 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7298. Min Act: -0.0000

Data Index: 739516 (The Pile)

Max Activating Token Index: 768

Text #16

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7857. Min Act: -0.0000

Data Index: 817102 (The Pile)

Max Activating Token Index: 801

Text #17

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1130093 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7703. Min Act: -0.0000

Data Index: 363993 (The Pile)

Max Activating Token Index: 634

Text #19

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7432. Min Act: -0.0000

Data Index: 902204 (The Pile)

Max Activating Token Index: 991