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

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

Neuron 4381 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.9915. Min Act: -0.0001

Data Index: 716856 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.7418. Min Act: -0.0000

Data Index: 289857 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.9913. Min Act: -0.0000

Data Index: 1002216 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.6968. Min Act: -0.0000

Data Index: 1294463 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.8638. Min Act: -0.0001

Data Index: 386488 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.6536. Min Act: -0.0001

Data Index: 1310695 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.8166. Min Act: -0.0000

Data Index: 336280 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.0383. Min Act: -0.0000

Data Index: 1354147 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.5298. Min Act: -0.0001

Data Index: 63651 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.3096. Min Act: -0.0000

Data Index: 652988 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.4737. Min Act: -0.0000

Data Index: 587014 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.2761. Min Act: -0.0000

Data Index: 1351847 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.4151. Min Act: -0.0000

Data Index: 554140 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.4154. Min Act: -0.0000

Data Index: 471149 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.3787. Min Act: -0.0000

Data Index: 1225362 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.3533. Min Act: -0.0000

Data Index: 1008050 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.3882. Min Act: -0.0000

Data Index: 1197067 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.5403. Min Act: -0.0000

Data Index: 342779 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.0104. Min Act: -0.0000

Data Index: 642098 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 4.9915. Min Range: -4.9915

Max Act: 4.3373. Min Act: -0.0000

Data Index: 142390 (C4 (Web Text))

Max Activating Token Index: 202