Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3171 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.5967. Min Act: -0.0000

Data Index: 394058 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.2786. Min Act: 0.0000

Data Index: 1005631 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.1030. Min Act: -0.0000

Data Index: 341022 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.2139. Min Act: -0.0000

Data Index: 83917 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.3572. Min Act: -0.0000

Data Index: 1167232 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.1383. Min Act: -0.0000

Data Index: 45292 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.1825. Min Act: -0.0000

Data Index: 259504 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1081336 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.1290. Min Act: -0.0000

Data Index: 1028894 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.1172. Min Act: 0.0000

Data Index: 646691 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.0719. Min Act: -0.0000

Data Index: 521469 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.0603. Min Act: -0.0000

Data Index: 37751 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.1018. Min Act: 0.0000

Data Index: 288768 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.0782. Min Act: -0.0000

Data Index: 843192 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.0129. Min Act: -0.0000

Data Index: 122835 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1135338 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.0491. Min Act: 0.0000

Data Index: 1111517 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 1.5967. Min Range: -1.5967

Max Act: 0.9924. Min Act: -0.0000

Data Index: 534175 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 1.5967. Min Range: -1.5967

Max Act: 0.9915. Min Act: -0.0000

Data Index: 480188 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.0567. Min Act: -0.0000

Data Index: 640839 (C4 (Web Text))

Max Activating Token Index: 805