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

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

Neuron 4798 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8046. Min Range: -2.8046

Max Act: 2.8046. Min Act: -0.0000

Data Index: 442628 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 2.8046. Min Range: -2.8046

Max Act: 2.4670. Min Act: -0.0000

Data Index: 254074 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 2.8046. Min Range: -2.8046

Max Act: 2.2536. Min Act: -0.0000

Data Index: 2427 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 2.8046. Min Range: -2.8046

Max Act: 2.2042. Min Act: -0.0000

Data Index: 271337 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 2.8046. Min Range: -2.8046

Max Act: 2.1923. Min Act: -0.0000

Data Index: 809823 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 2.8046. Min Range: -2.8046

Max Act: 2.0599. Min Act: -0.0000

Data Index: 642910 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 2.8046. Min Range: -2.8046

Max Act: 1.9901. Min Act: -0.0000

Data Index: 189594 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 2.8046. Min Range: -2.8046

Max Act: 1.8774. Min Act: -0.0000

Data Index: 78619 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 2.8046. Min Range: -2.8046

Max Act: 1.8482. Min Act: -0.0000

Data Index: 909898 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 2.8046. Min Range: -2.8046

Max Act: 1.9700. Min Act: -0.0000

Data Index: 890229 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 2.8046. Min Range: -2.8046

Max Act: 1.8474. Min Act: -0.0000

Data Index: 230645 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 2.8046. Min Range: -2.8046

Max Act: 2.0221. Min Act: -0.0000

Data Index: 1212529 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 2.8046. Min Range: -2.8046

Max Act: 2.0172. Min Act: -0.0000

Data Index: 1285905 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 2.8046. Min Range: -2.8046

Max Act: 2.0113. Min Act: -0.0000

Data Index: 77313 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 2.8046. Min Range: -2.8046

Max Act: 1.7493. Min Act: -0.0000

Data Index: 608794 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 2.8046. Min Range: -2.8046

Max Act: 1.9292. Min Act: -0.0000

Data Index: 1247667 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 2.8046. Min Range: -2.8046

Max Act: 1.7885. Min Act: -0.0000

Data Index: 1105808 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 2.8046. Min Range: -2.8046

Max Act: 1.7096. Min Act: -0.0000

Data Index: 1275565 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 2.8046. Min Range: -2.8046

Max Act: 1.7217. Min Act: -0.0000

Data Index: 648150 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 2.8046. Min Range: -2.8046

Max Act: 1.6134. Min Act: -0.0000

Data Index: 749326 (C4 (Web Text))

Max Activating Token Index: 1001