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

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

Neuron 4531 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1776. Min Act: -0.0000

Data Index: 356405 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.5889. Min Act: -0.0000

Data Index: 688239 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.5557. Min Act: -0.0000

Data Index: 703218 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1185. Min Act: -0.0000

Data Index: 796377 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.3008. Min Act: -0.0000

Data Index: 920531 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.2821. Min Act: -0.0000

Data Index: 1242470 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.0679. Min Act: -0.0000

Data Index: 1016339 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.0501. Min Act: -0.0000

Data Index: 465244 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.0444. Min Act: -0.0000

Data Index: 921893 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.2278. Min Act: -0.0000

Data Index: 447806 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.0319. Min Act: -0.0000

Data Index: 966736 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1915. Min Act: -0.0000

Data Index: 499887 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1826. Min Act: -0.0000

Data Index: 1079545 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.2029. Min Act: -0.0000

Data Index: 228142 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 5.5889. Min Range: -5.5889

Max Act: 4.8003. Min Act: -0.0000

Data Index: 111508 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1362. Min Act: -0.0000

Data Index: 802668 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1559. Min Act: -0.0000

Data Index: 235855 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 5.5889. Min Range: -5.5889

Max Act: 4.9758. Min Act: -0.0000

Data Index: 959855 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1374. Min Act: -0.0000

Data Index: 1177732 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1196. Min Act: -0.0000

Data Index: 605837 (C4 (Web Text))

Max Activating Token Index: 535