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

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

Neuron 5103 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0988. Min Range: -2.0988

Max Act: 2.0988. Min Act: -0.0000

Data Index: 287527 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.6214. Min Act: -0.0000

Data Index: 197466 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.3460. Min Act: -0.0000

Data Index: 853244 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.3967. Min Act: -0.0000

Data Index: 264215 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.3293. Min Act: -0.0000

Data Index: 1115357 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.3113. Min Act: -0.0000

Data Index: 1176302 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.2384. Min Act: -0.0000

Data Index: 513656 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.2307. Min Act: -0.0000

Data Index: 1358800 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.1864. Min Act: -0.0000

Data Index: 422925 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.1776. Min Act: -0.0000

Data Index: 1083454 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.1616. Min Act: -0.0000

Data Index: 805022 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.1002. Min Act: -0.0000

Data Index: 206598 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.0962. Min Act: -0.0000

Data Index: 870160 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.0472. Min Act: -0.0000

Data Index: 694035 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.0417. Min Act: -0.0000

Data Index: 274457 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 2.0988. Min Range: -2.0988

Max Act: 0.9733. Min Act: -0.0000

Data Index: 1020810 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.0297. Min Act: -0.0000

Data Index: 336147 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.0333. Min Act: -0.0000

Data Index: 58113 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 2.0988. Min Range: -2.0988

Max Act: 1.0133. Min Act: -0.0000

Data Index: 829691 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 2.0988. Min Range: -2.0988

Max Act: 0.9508. Min Act: -0.0000

Data Index: 213484 (C4 (Web Text))

Max Activating Token Index: 578