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

Dataset: The Pile

Neuron 1637 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.5252. Min Act: -0.0000

Data Index: 1661701 (The Pile)

Max Activating Token Index: 678

Text #1

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3351. Min Act: -0.0000

Data Index: 703524 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.4353. Min Act: 0.0000

Data Index: 763295 (The Pile)

Max Activating Token Index: 664

Text #3

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3267. Min Act: -0.0000

Data Index: 608183 (The Pile)

Max Activating Token Index: 942

Text #4

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.2944. Min Act: -0.0000

Data Index: 1035018 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.2276. Min Act: 0.0000

Data Index: 683038 (The Pile)

Max Activating Token Index: 791

Text #6

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.1911. Min Act: -0.0000

Data Index: 267114 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 1.5252. Min Range: -1.5252

Max Act: 0.9504. Min Act: -0.0000

Data Index: 785225 (The Pile)

Max Activating Token Index: 107

Text #8

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.0067. Min Act: 0.0000

Data Index: 55947 (The Pile)

Max Activating Token Index: 862

Text #9

Max Range: 1.5252. Min Range: -1.5252

Max Act: 0.9341. Min Act: -0.0000

Data Index: 59271 (The Pile)

Max Activating Token Index: 444

Text #10

Max Range: 1.5252. Min Range: -1.5252

Max Act: 0.9959. Min Act: -0.0000

Data Index: 267907 (The Pile)

Max Activating Token Index: 878

Text #11

Max Range: 1.5252. Min Range: -1.5252

Max Act: 0.9713. Min Act: -0.0000

Data Index: 667039 (The Pile)

Max Activating Token Index: 454

Text #12

Max Range: 1.5252. Min Range: -1.5252

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1295003 (The Pile)

Max Activating Token Index: 914

Text #13

Max Range: 1.5252. Min Range: -1.5252

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1348858 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 1.5252. Min Range: -1.5252

Max Act: 0.8938. Min Act: -0.0000

Data Index: 235266 (The Pile)

Max Activating Token Index: 828

Text #15

Max Range: 1.5252. Min Range: -1.5252

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1672573 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 1.5252. Min Range: -1.5252

Max Act: 0.9391. Min Act: -0.0000

Data Index: 1145019 (The Pile)

Max Activating Token Index: 127

Text #17

Max Range: 1.5252. Min Range: -1.5252

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1965341 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 1.5252. Min Range: -1.5252

Max Act: 0.7861. Min Act: -0.0000

Data Index: 887238 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 1.5252. Min Range: -1.5252

Max Act: 0.7962. Min Act: -0.0000

Data Index: 570381 (The Pile)

Max Activating Token Index: 703