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

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

Neuron 3496 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1096828 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1055947 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.7492. Min Act: -0.0000

Data Index: 873929 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.7745. Min Act: -0.0000

Data Index: 87743 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1272733 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1268003 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.6653. Min Act: -0.0000

Data Index: 497508 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.8154. Min Act: -0.0000

Data Index: 219310 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.6735. Min Act: -0.0000

Data Index: 970651 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1206469 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.7815. Min Act: -0.0000

Data Index: 614627 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.7709. Min Act: -0.0000

Data Index: 220041 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.6438. Min Act: -0.0001

Data Index: 587134 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.7516. Min Act: -0.0000

Data Index: 1019415 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.6676. Min Act: -0.0000

Data Index: 658903 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.6600. Min Act: -0.0000

Data Index: 324114 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.5974. Min Act: -0.0000

Data Index: 110014 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.7306. Min Act: -0.0000

Data Index: 338873 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.6156. Min Act: -0.0000

Data Index: 888493 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.8154. Min Range: -0.8154

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1166448 (C4 (Web Text))

Max Activating Token Index: 704