Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2352 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0915. Min Range: -1.0915

Max Act: 1.0915. Min Act: -0.0000

Data Index: 403345 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 1.0915. Min Range: -1.0915

Max Act: 1.0893. Min Act: -0.0000

Data Index: 1221459 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 1.0915. Min Range: -1.0915

Max Act: 1.0705. Min Act: -0.0001

Data Index: 602775 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 1.0915. Min Range: -1.0915

Max Act: 1.0235. Min Act: -0.0000

Data Index: 251108 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.9873. Min Act: -0.0001

Data Index: 978289 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 1.0915. Min Range: -1.0915

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1133221 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.9655. Min Act: -0.0000

Data Index: 131660 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.9593. Min Act: -0.0001

Data Index: 220273 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.9527. Min Act: -0.0001

Data Index: 740498 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.9677. Min Act: -0.0000

Data Index: 391903 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.9630. Min Act: -0.0001

Data Index: 855276 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.9302. Min Act: -0.0001

Data Index: 131210 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.9039. Min Act: -0.0000

Data Index: 538993 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.9476. Min Act: -0.0001

Data Index: 536980 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.9051. Min Act: -0.0000

Data Index: 984927 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.9072. Min Act: -0.0000

Data Index: 784995 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.8974. Min Act: -0.0001

Data Index: 207725 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.8493. Min Act: -0.0000

Data Index: 188265 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.8875. Min Act: -0.0000

Data Index: 586252 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.8632. Min Act: -0.0001

Data Index: 882988 (C4 (Web Text))

Max Activating Token Index: 824