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

Dataset: The Pile

Neuron 4235 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: 4.3949. Min Range: -4.3949

Max Act: 4.3949. Min Act: -0.0000

Data Index: 402239 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 4.3949. Min Range: -4.3949

Max Act: 4.0875. Min Act: -0.0000

Data Index: 1327337 (The Pile)

Max Activating Token Index: 974

Text #2

Max Range: 4.3949. Min Range: -4.3949

Max Act: 4.1299. Min Act: -0.0000

Data Index: 563589 (The Pile)

Max Activating Token Index: 790

Text #3

Max Range: 4.3949. Min Range: -4.3949

Max Act: 4.0108. Min Act: -0.0000

Data Index: 1833454 (The Pile)

Max Activating Token Index: 876

Text #4

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.8477. Min Act: -0.0000

Data Index: 1527796 (The Pile)

Max Activating Token Index: 536

Text #5

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.9430. Min Act: -0.0000

Data Index: 1775177 (The Pile)

Max Activating Token Index: 691

Text #6

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.8412. Min Act: -0.0000

Data Index: 583826 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.8541. Min Act: -0.0000

Data Index: 1470638 (The Pile)

Max Activating Token Index: 42

Text #8

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.8305. Min Act: -0.0000

Data Index: 1923932 (The Pile)

Max Activating Token Index: 167

Text #9

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.7576. Min Act: -0.0000

Data Index: 188900 (The Pile)

Max Activating Token Index: 857

Text #10

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.9268. Min Act: -0.0000

Data Index: 1182276 (The Pile)

Max Activating Token Index: 863

Text #11

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.4045. Min Act: -0.0000

Data Index: 942964 (The Pile)

Max Activating Token Index: 116

Text #12

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.7120. Min Act: -0.0000

Data Index: 728495 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.9047. Min Act: -0.0000

Data Index: 1659963 (The Pile)

Max Activating Token Index: 124

Text #14

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.3340. Min Act: -0.0000

Data Index: 1045721 (The Pile)

Max Activating Token Index: 191

Text #15

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.8138. Min Act: -0.0000

Data Index: 134906 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.4480. Min Act: -0.0000

Data Index: 1920827 (The Pile)

Max Activating Token Index: 723

Text #17

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.1354. Min Act: -0.0000

Data Index: 1236841 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.2272. Min Act: -0.0000

Data Index: 479540 (The Pile)

Max Activating Token Index: 371

Text #19

Max Range: 4.3949. Min Range: -4.3949

Max Act: 3.4270. Min Act: -0.0000

Data Index: 41586 (The Pile)

Max Activating Token Index: 327