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

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

Neuron 2755 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: 1.2233. Min Range: -1.2233

Max Act: 1.2233. Min Act: -0.0000

Data Index: 746359 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 1.2233. Min Range: -1.2233

Max Act: 1.0471. Min Act: -0.0000

Data Index: 785999 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 1.2233. Min Range: -1.2233

Max Act: 1.0372. Min Act: -0.0000

Data Index: 1331714 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 1.2233. Min Range: -1.2233

Max Act: 1.0074. Min Act: -0.0000

Data Index: 779939 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 1.2233. Min Range: -1.2233

Max Act: 1.0866. Min Act: -0.0000

Data Index: 1257843 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 1.2233. Min Range: -1.2233

Max Act: 0.8709. Min Act: -0.0000

Data Index: 484599 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 1.2233. Min Range: -1.2233

Max Act: 0.8919. Min Act: -0.0000

Data Index: 1457341 (Python Code)

Max Activating Token Index: 571

Text #7

Max Range: 1.2233. Min Range: -1.2233

Max Act: 0.9265. Min Act: -0.0000

Data Index: 765214 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 1.2233. Min Range: -1.2233

Max Act: 0.9877. Min Act: -0.0000

Data Index: 282206 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 1.2233. Min Range: -1.2233

Max Act: 0.9662. Min Act: -0.0000

Data Index: 380808 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 1.2233. Min Range: -1.2233

Max Act: 0.9383. Min Act: -0.0000

Data Index: 133835 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 1.2233. Min Range: -1.2233

Max Act: 0.9274. Min Act: -0.0000

Data Index: 205590 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 1.2233. Min Range: -1.2233

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1243297 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 1.2233. Min Range: -1.2233

Max Act: 0.9319. Min Act: -0.0000

Data Index: 840707 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 1.2233. Min Range: -1.2233

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1070183 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 1.2233. Min Range: -1.2233

Max Act: 0.8129. Min Act: -0.0000

Data Index: 1512065 (Python Code)

Max Activating Token Index: 677

Text #16

Max Range: 1.2233. Min Range: -1.2233

Max Act: 0.8473. Min Act: -0.0000

Data Index: 6609 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 1.2233. Min Range: -1.2233

Max Act: 0.7887. Min Act: -0.0000

Data Index: 850293 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 1.2233. Min Range: -1.2233

Max Act: 0.7841. Min Act: -0.0000

Data Index: 216714 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 1.2233. Min Range: -1.2233

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1133451 (C4 (Web Text))

Max Activating Token Index: 41