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

Dataset: The Pile

Neuron 1450 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.4054. Min Act: -0.0000

Data Index: 908379 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.3282. Min Act: -0.0000

Data Index: 1041944 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2721. Min Act: -0.0000

Data Index: 1367162 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2899. Min Act: -0.0000

Data Index: 1509391 (The Pile)

Max Activating Token Index: 863

Text #4

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.3371. Min Act: -0.0000

Data Index: 779235 (The Pile)

Max Activating Token Index: 574

Text #5

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2514. Min Act: -0.0000

Data Index: 957144 (The Pile)

Max Activating Token Index: 981

Text #6

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2481. Min Act: -0.0000

Data Index: 1251227 (The Pile)

Max Activating Token Index: 60

Text #7

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1792. Min Act: -0.0000

Data Index: 176436 (The Pile)

Max Activating Token Index: 544

Text #8

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.3109. Min Act: -0.0000

Data Index: 1965212 (The Pile)

Max Activating Token Index: 342

Text #9

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2302. Min Act: -0.0000

Data Index: 1027625 (The Pile)

Max Activating Token Index: 220

Text #10

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1913. Min Act: -0.0000

Data Index: 577524 (The Pile)

Max Activating Token Index: 872

Text #11

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1380. Min Act: -0.0000

Data Index: 1793902 (The Pile)

Max Activating Token Index: 847

Text #12

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2665. Min Act: -0.0000

Data Index: 1921075 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1196. Min Act: -0.0000

Data Index: 340152 (The Pile)

Max Activating Token Index: 239

Text #14

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1427. Min Act: -0.0000

Data Index: 281716 (The Pile)

Max Activating Token Index: 758

Text #15

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2039. Min Act: -0.0000

Data Index: 1829403 (The Pile)

Max Activating Token Index: 408

Text #16

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1431. Min Act: -0.0000

Data Index: 1196245 (The Pile)

Max Activating Token Index: 657

Text #17

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1745. Min Act: -0.0000

Data Index: 542016 (The Pile)

Max Activating Token Index: 948

Text #18

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1962. Min Act: -0.0000

Data Index: 1538082 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.0898. Min Act: -0.0000

Data Index: 786132 (The Pile)

Max Activating Token Index: 281