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

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

Neuron 1876 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.3246. Min Act: -0.0000

Data Index: 447937 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.9688. Min Act: -0.0000

Data Index: 1241927 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.9860. Min Act: -0.0000

Data Index: 630953 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.9391. Min Act: -0.0000

Data Index: 413634 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.9143. Min Act: -0.0000

Data Index: 96466 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.8650. Min Act: -0.0000

Data Index: 124892 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.8545. Min Act: -0.0000

Data Index: 889924 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.8265. Min Act: -0.0000

Data Index: 519349 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.8355. Min Act: -0.0000

Data Index: 149088 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.8205. Min Act: -0.0000

Data Index: 43147 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.7869. Min Act: -0.0000

Data Index: 169809 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1324003 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.7812. Min Act: -0.0000

Data Index: 53465 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.7711. Min Act: -0.0000

Data Index: 785113 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.7421. Min Act: -0.0000

Data Index: 150267 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.7529. Min Act: -0.0000

Data Index: 769977 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.7263. Min Act: -0.0000

Data Index: 368630 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.7090. Min Act: -0.0000

Data Index: 286357 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1079603 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 1.3246. Min Range: -1.3246

Max Act: 0.7702. Min Act: -0.0000

Data Index: 511266 (C4 (Web Text))

Max Activating Token Index: 304