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

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

Neuron 3495 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: 1.5178. Min Range: -1.5178

Max Act: 1.5178. Min Act: -0.0002

Data Index: 668406 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.2186. Min Act: -0.0002

Data Index: 471710 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.1121. Min Act: -0.0002

Data Index: 1104592 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.0633. Min Act: -0.0002

Data Index: 503836 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.0752. Min Act: -0.0002

Data Index: 1195686 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 1.5178. Min Range: -1.5178

Max Act: 0.9763. Min Act: -0.0002

Data Index: 132160 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.0497. Min Act: -0.0002

Data Index: 505347 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.1117. Min Act: -0.0002

Data Index: 1091083 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.0189. Min Act: -0.0002

Data Index: 538890 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 1.5178. Min Range: -1.5178

Max Act: 0.9847. Min Act: -0.0002

Data Index: 1063484 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.0089. Min Act: -0.0002

Data Index: 1014974 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 1.5178. Min Range: -1.5178

Max Act: 0.9478. Min Act: -0.0002

Data Index: 381510 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.0018. Min Act: -0.0002

Data Index: 249828 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 1.5178. Min Range: -1.5178

Max Act: 0.9913. Min Act: -0.0002

Data Index: 984639 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 1.5178. Min Range: -1.5178

Max Act: 0.9781. Min Act: -0.0002

Data Index: 461374 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.0369. Min Act: -0.0002

Data Index: 173566 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 1.5178. Min Range: -1.5178

Max Act: 0.9773. Min Act: -0.0002

Data Index: 1152690 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 1.5178. Min Range: -1.5178

Max Act: 0.9419. Min Act: -0.0002

Data Index: 277391 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 1.5178. Min Range: -1.5178

Max Act: 0.9389. Min Act: -0.0002

Data Index: 1133279 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 1.5178. Min Range: -1.5178

Max Act: 0.9307. Min Act: -0.0002

Data Index: 536160 (C4 (Web Text))

Max Activating Token Index: 142