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

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

Neuron 1087 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.6230. Min Act: -0.0000

Data Index: 438420 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.5183. Min Act: -0.0000

Data Index: 725638 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.4931. Min Act: -0.0000

Data Index: 119848 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.3820. Min Act: -0.0000

Data Index: 838706 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.4614. Min Act: -0.0000

Data Index: 448381 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.4731. Min Act: -0.0000

Data Index: 40422 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.4619. Min Act: -0.0000

Data Index: 1168058 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.4348. Min Act: -0.0000

Data Index: 611443 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.4770. Min Act: -0.0000

Data Index: 156916 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.3597. Min Act: -0.0000

Data Index: 202650 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.3340. Min Act: -0.0000

Data Index: 801526 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.4428. Min Act: -0.0000

Data Index: 570875 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.3770. Min Act: -0.0000

Data Index: 442603 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.2928. Min Act: -0.0000

Data Index: 857495 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.3226. Min Act: -0.0000

Data Index: 830014 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.3249. Min Act: -0.0000

Data Index: 50905 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.3445. Min Act: -0.0000

Data Index: 1004625 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.4842. Min Act: -0.0000

Data Index: 659992 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.2898. Min Act: -0.0000

Data Index: 731466 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 1.6230. Min Range: -1.6230

Max Act: 1.2543. Min Act: -0.0000

Data Index: 483794 (C4 (Web Text))

Max Activating Token Index: 387