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

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

Neuron 1424 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.5442. Min Act: -0.0001

Data Index: 1081271 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.7580. Min Act: -0.0001

Data Index: 623719 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3077. Min Act: -0.0001

Data Index: 1026153 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3960. Min Act: -0.0001

Data Index: 425768 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.2803. Min Act: -0.0001

Data Index: 865079 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3203. Min Act: -0.0001

Data Index: 881224 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3894. Min Act: -0.0001

Data Index: 855850 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.2445. Min Act: -0.0001

Data Index: 523972 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.2354. Min Act: -0.0001

Data Index: 888135 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.2036. Min Act: -0.0001

Data Index: 411602 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.2047. Min Act: -0.0001

Data Index: 826009 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.0648. Min Act: -0.0001

Data Index: 59738 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.2554. Min Act: -0.0001

Data Index: 329687 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.3046. Min Act: -0.0001

Data Index: 529606 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.2328. Min Act: -0.0001

Data Index: 894843 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.4432. Min Act: -0.0001

Data Index: 899459 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.0690. Min Act: -0.0001

Data Index: 3343 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.0200. Min Act: -0.0001

Data Index: 1044466 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.1851. Min Act: -0.0001

Data Index: 335271 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.1439. Min Act: -0.0001

Data Index: 233933 (C4 (Web Text))

Max Activating Token Index: 426