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

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

Neuron 3269 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6937. Min Act: -0.0000

Data Index: 55411 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1101094 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6425. Min Act: -0.0000

Data Index: 1315398 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6041. Min Act: -0.0000

Data Index: 122047 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6160. Min Act: -0.0000

Data Index: 296581 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5854. Min Act: -0.0000

Data Index: 489564 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5772. Min Act: -0.0000

Data Index: 528417 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5716. Min Act: -0.0000

Data Index: 244261 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5498. Min Act: -0.0000

Data Index: 867914 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5452. Min Act: -0.0000

Data Index: 583048 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1122450 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5835. Min Act: -0.0000

Data Index: 328371 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1073390 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6009. Min Act: -0.0000

Data Index: 869012 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5222. Min Act: -0.0000

Data Index: 408267 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5088. Min Act: -0.0000

Data Index: 348954 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5666. Min Act: -0.0000

Data Index: 827894 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5280. Min Act: -0.0000

Data Index: 67905 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5231. Min Act: -0.0000

Data Index: 578088 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1121373 (C4 (Web Text))

Max Activating Token Index: 301