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

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

Neuron 2622 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: 1.9047. Min Range: -1.9047

Max Act: 1.9047. Min Act: -0.0000

Data Index: 853833 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7240. Min Act: -0.0000

Data Index: 1192800 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7242. Min Act: -0.0000

Data Index: 1148908 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6897. Min Act: -0.0000

Data Index: 89861 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6761. Min Act: -0.0000

Data Index: 836803 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6153. Min Act: -0.0000

Data Index: 788497 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6455. Min Act: -0.0000

Data Index: 970724 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6888. Min Act: -0.0000

Data Index: 182586 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5876. Min Act: -0.0000

Data Index: 760291 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5862. Min Act: -0.0000

Data Index: 1093195 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5600. Min Act: -0.0000

Data Index: 658059 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5199. Min Act: -0.0000

Data Index: 867785 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5352. Min Act: -0.0000

Data Index: 826953 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5598. Min Act: -0.0000

Data Index: 736462 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5591. Min Act: -0.0000

Data Index: 990107 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5464. Min Act: -0.0000

Data Index: 907767 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5381. Min Act: -0.0000

Data Index: 87928 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5458. Min Act: -0.0000

Data Index: 624748 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.4569. Min Act: -0.0000

Data Index: 606445 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6042. Min Act: -0.0000

Data Index: 1180412 (C4 (Web Text))

Max Activating Token Index: 842