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

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

Neuron 1729 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: 0.9076. Min Range: -0.9076

Max Act: 0.9076. Min Act: -0.0000

Data Index: 863980 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7192. Min Act: -0.0000

Data Index: 438339 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.6564. Min Act: -0.0000

Data Index: 289136 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.6982. Min Act: -0.0000

Data Index: 801502 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7128. Min Act: -0.0000

Data Index: 441910 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7029. Min Act: -0.0000

Data Index: 82317 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.6893. Min Act: -0.0000

Data Index: 136190 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.5951. Min Act: -0.0000

Data Index: 209821 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.6545. Min Act: -0.0000

Data Index: 618941 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.5800. Min Act: 0.0000

Data Index: 568241 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.6411. Min Act: 0.0000

Data Index: 563136 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.6576. Min Act: -0.0000

Data Index: 418313 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.5939. Min Act: -0.0000

Data Index: 221809 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.6325. Min Act: -0.0000

Data Index: 530007 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.5687. Min Act: -0.0000

Data Index: 389320 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.5608. Min Act: -0.0000

Data Index: 694639 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1164614 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1215092 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1176331 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1318842 (C4 (Web Text))

Max Activating Token Index: 418