Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 437 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.9344. Min Act: -0.0000

Data Index: 1028808 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.3032. Min Act: -0.0001

Data Index: 173009 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.2580. Min Act: -0.0000

Data Index: 3137 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.2435. Min Act: -0.0000

Data Index: 304499 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.0750. Min Act: -0.0000

Data Index: 1100870 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.0879. Min Act: -0.0000

Data Index: 527147 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.0152. Min Act: -0.0000

Data Index: 491748 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 1.9344. Min Range: -1.9344

Max Act: 0.9279. Min Act: -0.0000

Data Index: 112887 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 1.9344. Min Range: -1.9344

Max Act: 0.9035. Min Act: -0.0000

Data Index: 473007 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 1.9344. Min Range: -1.9344

Max Act: 0.8576. Min Act: -0.0000

Data Index: 1089541 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 1.9344. Min Range: -1.9344

Max Act: 0.8416. Min Act: -0.0000

Data Index: 683228 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 1.9344. Min Range: -1.9344

Max Act: 0.8067. Min Act: -0.0000

Data Index: 292872 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 1.9344. Min Range: -1.9344

Max Act: 0.8750. Min Act: -0.0001

Data Index: 290803 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 1.9344. Min Range: -1.9344

Max Act: 0.7696. Min Act: -0.0001

Data Index: 567281 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 1.9344. Min Range: -1.9344

Max Act: 0.7674. Min Act: -0.0000

Data Index: 682443 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.9344. Min Range: -1.9344

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1245535 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 1.9344. Min Range: -1.9344

Max Act: 0.7501. Min Act: -0.0001

Data Index: 1036950 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 1.9344. Min Range: -1.9344

Max Act: 0.7406. Min Act: -0.0000

Data Index: 99922 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 1.9344. Min Range: -1.9344

Max Act: 0.7603. Min Act: -0.0001

Data Index: 40826 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 1.9344. Min Range: -1.9344

Max Act: 0.7382. Min Act: -0.0001

Data Index: 429554 (C4 (Web Text))

Max Activating Token Index: 349