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

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

Neuron 4414 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0999. Min Range: -1.0999

Max Act: 1.0999. Min Act: 0.0001

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.8741. Min Act: 0.0001

Data Index: 1164353 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.7504. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1302923 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.7196. Min Act: -0.0000

Data Index: 865420 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.7067. Min Act: -0.0000

Data Index: 992564 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.5549. Min Act: 0.0000

Data Index: 113207 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.6340. Min Act: -0.0000

Data Index: 1221173 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1014937 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1052269 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.6012. Min Act: 0.0000

Data Index: 1067830 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.5264. Min Act: -0.0000

Data Index: 901682 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.5759. Min Act: 0.0000

Data Index: 679546 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.5876. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.6157. Min Act: -0.0000

Data Index: 487882 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.4644. Min Act: 0.0000

Data Index: 180133 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1099132 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.4957. Min Act: -0.0000

Data Index: 1287935 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.4918. Min Act: -0.0000

Data Index: 843624 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.4553. Min Act: -0.0000

Data Index: 454027 (C4 (Web Text))

Max Activating Token Index: 777