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

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

Neuron 1051 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: 0.7389. Min Range: -0.7389

Max Act: 0.7389. Min Act: -0.0000

Data Index: 584238 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6881. Min Act: -0.0000

Data Index: 725739 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6782. Min Act: -0.0000

Data Index: 614982 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1288086 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6306. Min Act: -0.0000

Data Index: 796112 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6211. Min Act: -0.0000

Data Index: 41720 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6826. Min Act: -0.0000

Data Index: 791041 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6671. Min Act: -0.0000

Data Index: 16676 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6020. Min Act: -0.0000

Data Index: 905305 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6448. Min Act: -0.0000

Data Index: 66662 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6413. Min Act: -0.0000

Data Index: 849337 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6081. Min Act: -0.0000

Data Index: 45655 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1053607 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5746. Min Act: -0.0000

Data Index: 751296 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6037. Min Act: -0.0000

Data Index: 107131 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5675. Min Act: -0.0000

Data Index: 394324 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1149295 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5579. Min Act: -0.0000

Data Index: 186898 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5524. Min Act: -0.0000

Data Index: 708481 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1123857 (C4 (Web Text))

Max Activating Token Index: 686