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

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

Neuron 3401 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.8602. Min Act: -0.0000

Data Index: 333967 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.7928. Min Act: -0.0000

Data Index: 64889 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.6501. Min Act: -0.0000

Data Index: 303633 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.7335. Min Act: -0.0000

Data Index: 397081 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.7218. Min Act: -0.0000

Data Index: 1108893 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.6991. Min Act: -0.0000

Data Index: 1106331 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.7079. Min Act: -0.0000

Data Index: 81921 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.6708. Min Act: -0.0000

Data Index: 426644 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.6493. Min Act: -0.0000

Data Index: 1094942 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.5348. Min Act: -0.0000

Data Index: 88062 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.6542. Min Act: -0.0000

Data Index: 1072855 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.6645. Min Act: -0.0000

Data Index: 615771 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.5500. Min Act: -0.0000

Data Index: 343056 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.4549. Min Act: -0.0000

Data Index: 462605 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.6332. Min Act: -0.0000

Data Index: 454566 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.6332. Min Act: -0.0000

Data Index: 57314 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.7224. Min Act: -0.0000

Data Index: 1180505 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.7409. Min Act: -0.0000

Data Index: 427705 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.5309. Min Act: -0.0000

Data Index: 744972 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 1.8602. Min Range: -1.8602

Max Act: 1.8319. Min Act: -0.0000

Data Index: 296823 (C4 (Web Text))

Max Activating Token Index: 776