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

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

Neuron 2770 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.6809. Min Act: -0.0002

Data Index: 357325 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.7180. Min Act: -0.0002

Data Index: 1234124 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5428. Min Act: -0.0002

Data Index: 638001 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.6826. Min Act: -0.0002

Data Index: 1189474 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5647. Min Act: -0.0002

Data Index: 628807 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.6468. Min Act: -0.0002

Data Index: 795369 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5920. Min Act: -0.0002

Data Index: 1220872 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.6282. Min Act: -0.0002

Data Index: 1200392 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.6410. Min Act: -0.0002

Data Index: 1288285 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5879. Min Act: -0.0002

Data Index: 1049445 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5286. Min Act: -0.0002

Data Index: 362481 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4953. Min Act: -0.0002

Data Index: 557457 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4930. Min Act: -0.0002

Data Index: 950893 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5725. Min Act: -0.0002

Data Index: 1326412 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4872. Min Act: -0.0002

Data Index: 151719 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5247. Min Act: -0.0002

Data Index: 1228597 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4462. Min Act: -0.0002

Data Index: 330014 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5199. Min Act: -0.0002

Data Index: 621737 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5271. Min Act: -0.0002

Data Index: 513648 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5048. Min Act: -0.0002

Data Index: 905966 (C4 (Web Text))

Max Activating Token Index: 17