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

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

Neuron 2957 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.6170. Min Act: -0.0001

Data Index: 905672 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.6279. Min Act: -0.0001

Data Index: 519152 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7564. Min Act: -0.0001

Data Index: 46960 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.6221. Min Act: -0.0001

Data Index: 369521 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.6093. Min Act: -0.0001

Data Index: 1294860 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.5811. Min Act: -0.0001

Data Index: 1397795 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.5725. Min Act: -0.0001

Data Index: 283647 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.5308. Min Act: -0.0001

Data Index: 500982 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.5404. Min Act: -0.0001

Data Index: 383179 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.5533. Min Act: -0.0001

Data Index: 741386 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.5295. Min Act: -0.0001

Data Index: 1112598 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.5425. Min Act: -0.0001

Data Index: 21114 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.4985. Min Act: -0.0001

Data Index: 710671 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.4894. Min Act: -0.0001

Data Index: 712650 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.5178. Min Act: -0.0001

Data Index: 85886 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.5153. Min Act: -0.0001

Data Index: 1027540 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.4782. Min Act: -0.0001

Data Index: 613155 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.4371. Min Act: -0.0001

Data Index: 133183 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.4477. Min Act: -0.0001

Data Index: 1274713 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.4301. Min Act: -0.0001

Data Index: 1047423 (C4 (Web Text))

Max Activating Token Index: 36