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

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

Neuron 3795 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: 1.6076. Min Range: -1.6076

Max Act: 1.6076. Min Act: -0.0000

Data Index: 16810 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 1.6076. Min Range: -1.6076

Max Act: 1.1219. Min Act: -0.0000

Data Index: 1282373 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 1.6076. Min Range: -1.6076

Max Act: 1.0395. Min Act: -0.0000

Data Index: 752652 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 1.6076. Min Range: -1.6076

Max Act: 1.1313. Min Act: -0.0000

Data Index: 735652 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 1.6076. Min Range: -1.6076

Max Act: 1.0312. Min Act: -0.0000

Data Index: 622207 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 1.6076. Min Range: -1.6076

Max Act: 0.9864. Min Act: -0.0000

Data Index: 162684 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 1.6076. Min Range: -1.6076

Max Act: 1.0532. Min Act: -0.0000

Data Index: 830570 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 1.6076. Min Range: -1.6076

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1353523 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 1.6076. Min Range: -1.6076

Max Act: 1.0691. Min Act: -0.0000

Data Index: 560063 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 1.6076. Min Range: -1.6076

Max Act: 0.9645. Min Act: 0.0000

Data Index: 66188 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 1.6076. Min Range: -1.6076

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1101376 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 1.6076. Min Range: -1.6076

Max Act: 0.9752. Min Act: -0.0000

Data Index: 644046 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 1.6076. Min Range: -1.6076

Max Act: 0.9765. Min Act: -0.0000

Data Index: 225972 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.6076. Min Range: -1.6076

Max Act: 0.9657. Min Act: -0.0000

Data Index: 288487 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 1.6076. Min Range: -1.6076

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1013260 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 1.6076. Min Range: -1.6076

Max Act: 0.9485. Min Act: -0.0000

Data Index: 381610 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 1.6076. Min Range: -1.6076

Max Act: 0.9153. Min Act: -0.0000

Data Index: 231080 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 1.6076. Min Range: -1.6076

Max Act: 0.9029. Min Act: -0.0000

Data Index: 876118 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 1.6076. Min Range: -1.6076

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1107178 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 1.6076. Min Range: -1.6076

Max Act: 0.8512. Min Act: -0.0000

Data Index: 1353469 (C4 (Web Text))

Max Activating Token Index: 363