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

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

Neuron 2944 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: 0.9130. Min Range: -0.9130

Max Act: 0.9130. Min Act: -0.0000

Data Index: 752707 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7581. Min Act: -0.0000

Data Index: 436743 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1263566 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.8027. Min Act: -0.0000

Data Index: 359012 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7743. Min Act: -0.0000

Data Index: 437073 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7471. Min Act: -0.0000

Data Index: 994308 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7220. Min Act: -0.0000

Data Index: 816795 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1353290 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7426. Min Act: -0.0000

Data Index: 361369 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7464. Min Act: -0.0000

Data Index: 647495 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1064725 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7157. Min Act: -0.0000

Data Index: 186261 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.6895. Min Act: -0.0000

Data Index: 165617 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7589. Min Act: -0.0000

Data Index: 993096 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7360. Min Act: -0.0000

Data Index: 378745 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7400. Min Act: -0.0000

Data Index: 172757 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7348. Min Act: -0.0000

Data Index: 250441 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7107. Min Act: -0.0000

Data Index: 254827 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1121538 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7115. Min Act: -0.0000

Data Index: 215328 (C4 (Web Text))

Max Activating Token Index: 697