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

Dataset: The Pile

Neuron 1612 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.7099. Min Act: -0.0000

Data Index: 1435594 (The Pile)

Max Activating Token Index: 1016

Text #1

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.6026. Min Act: -0.0000

Data Index: 1747145 (The Pile)

Max Activating Token Index: 991

Text #2

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.3887. Min Act: -0.0000

Data Index: 208317 (The Pile)

Max Activating Token Index: 207

Text #3

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.4787. Min Act: -0.0000

Data Index: 277447 (The Pile)

Max Activating Token Index: 597

Text #4

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.2208. Min Act: -0.0000

Data Index: 852237 (The Pile)

Max Activating Token Index: 955

Text #5

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.4499. Min Act: -0.0000

Data Index: 1793281 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.1895. Min Act: -0.0000

Data Index: 1588087 (The Pile)

Max Activating Token Index: 196

Text #7

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.1588. Min Act: -0.0000

Data Index: 65590 (The Pile)

Max Activating Token Index: 866

Text #8

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.3332. Min Act: -0.0000

Data Index: 795141 (The Pile)

Max Activating Token Index: 684

Text #9

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.4161. Min Act: -0.0000

Data Index: 258976 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.3783. Min Act: -0.0000

Data Index: 940017 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.3686. Min Act: -0.0000

Data Index: 535834 (The Pile)

Max Activating Token Index: 709

Text #12

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.3246. Min Act: -0.0000

Data Index: 658113 (The Pile)

Max Activating Token Index: 269

Text #13

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.3176. Min Act: -0.0000

Data Index: 1882299 (The Pile)

Max Activating Token Index: 281

Text #14

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.2283. Min Act: -0.0000

Data Index: 1057406 (The Pile)

Max Activating Token Index: 283

Text #15

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.2184. Min Act: -0.0000

Data Index: 247377 (The Pile)

Max Activating Token Index: 826

Text #16

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1939087 (The Pile)

Max Activating Token Index: 972

Text #17

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.2862. Min Act: -0.0000

Data Index: 222567 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.1418. Min Act: -0.0000

Data Index: 635016 (The Pile)

Max Activating Token Index: 1014

Text #19

Max Range: 1.7099. Min Range: -1.7099

Max Act: 1.1999. Min Act: -0.0000

Data Index: 183957 (The Pile)

Max Activating Token Index: 176