Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1756 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.9851. Min Act: -0.0000

Data Index: 524767 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.8532. Min Act: -0.0000

Data Index: 719416 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.6377. Min Act: -0.0000

Data Index: 898408 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.5420. Min Act: -0.0000

Data Index: 1337597 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.5256. Min Act: -0.0000

Data Index: 828307 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.6695. Min Act: -0.0000

Data Index: 167809 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.0343. Min Act: -0.0000

Data Index: 978306 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.3084. Min Act: -0.0000

Data Index: 57774 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.1432. Min Act: -0.0000

Data Index: 193000 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.2768. Min Act: -0.0000

Data Index: 41503 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.0840. Min Act: -0.0000

Data Index: 755591 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.1421. Min Act: -0.0000

Data Index: 716475 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.0086. Min Act: -0.0000

Data Index: 1350346 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.0039. Min Act: -0.0000

Data Index: 482483 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.1562. Min Act: -0.0000

Data Index: 354837 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.1355. Min Act: -0.0000

Data Index: 1065063 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 3.9851. Min Range: -3.9851

Max Act: 2.9521. Min Act: -0.0000

Data Index: 714094 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 3.9851. Min Range: -3.9851

Max Act: 2.9034. Min Act: -0.0000

Data Index: 324810 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.0406. Min Act: -0.0000

Data Index: 636281 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.0275. Min Act: -0.0000

Data Index: 499511 (C4 (Web Text))

Max Activating Token Index: 665