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

Dataset: The Pile

Neuron 1551 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: 1.1235. Min Range: -1.1235

Max Act: 1.1235. Min Act: -0.0000

Data Index: 331833 (The Pile)

Max Activating Token Index: 702

Text #1

Max Range: 1.1235. Min Range: -1.1235

Max Act: 1.0927. Min Act: -0.0000

Data Index: 370548 (The Pile)

Max Activating Token Index: 285

Text #2

Max Range: 1.1235. Min Range: -1.1235

Max Act: 1.0699. Min Act: -0.0000

Data Index: 468000 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 1.1235. Min Range: -1.1235

Max Act: 1.0165. Min Act: -0.0000

Data Index: 1370337 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.9405. Min Act: -0.0000

Data Index: 600749 (The Pile)

Max Activating Token Index: 706

Text #5

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.9248. Min Act: -0.0000

Data Index: 1442976 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8931. Min Act: -0.0000

Data Index: 1432948 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8853. Min Act: -0.0000

Data Index: 186055 (The Pile)

Max Activating Token Index: 285

Text #8

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8775. Min Act: -0.0000

Data Index: 329374 (The Pile)

Max Activating Token Index: 219

Text #9

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8900. Min Act: -0.0000

Data Index: 840079 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1653582 (The Pile)

Max Activating Token Index: 81

Text #11

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.9186. Min Act: -0.0000

Data Index: 261470 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1131729 (The Pile)

Max Activating Token Index: 113

Text #13

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1876806 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1567032 (The Pile)

Max Activating Token Index: 554

Text #15

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8882. Min Act: -0.0000

Data Index: 1517384 (The Pile)

Max Activating Token Index: 80

Text #16

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.9051. Min Act: -0.0000

Data Index: 685693 (The Pile)

Max Activating Token Index: 59

Text #17

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1046056 (The Pile)

Max Activating Token Index: 305

Text #18

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.9108. Min Act: -0.0000

Data Index: 1643383 (The Pile)

Max Activating Token Index: 83

Text #19

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8245. Min Act: -0.0000

Data Index: 646893 (The Pile)

Max Activating Token Index: 385