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

Dataset: The Pile

Neuron 396 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1715770 (The Pile)

Max Activating Token Index: 718

Text #1

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1080253 (The Pile)

Max Activating Token Index: 979

Text #2

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1406222 (The Pile)

Max Activating Token Index: 823

Text #3

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1085535 (The Pile)

Max Activating Token Index: 708

Text #4

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1072658 (The Pile)

Max Activating Token Index: 943

Text #5

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5918. Min Act: -0.0000

Data Index: 1971427 (The Pile)

Max Activating Token Index: 541

Text #6

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5763. Min Act: -0.0000

Data Index: 940804 (The Pile)

Max Activating Token Index: 782

Text #7

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5743. Min Act: -0.0000

Data Index: 374136 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1120303 (The Pile)

Max Activating Token Index: 474

Text #9

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5302. Min Act: -0.0000

Data Index: 945723 (The Pile)

Max Activating Token Index: 984

Text #10

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5570. Min Act: -0.0000

Data Index: 167541 (The Pile)

Max Activating Token Index: 467

Text #11

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1517660 (The Pile)

Max Activating Token Index: 905

Text #12

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5678. Min Act: -0.0000

Data Index: 829997 (The Pile)

Max Activating Token Index: 702

Text #13

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1886002 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1307042 (The Pile)

Max Activating Token Index: 807

Text #15

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1179657 (The Pile)

Max Activating Token Index: 739

Text #16

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5406. Min Act: -0.0000

Data Index: 1316406 (The Pile)

Max Activating Token Index: 632

Text #17

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1915222 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5185. Min Act: -0.0000

Data Index: 388127 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5159. Min Act: -0.0000

Data Index: 242871 (The Pile)

Max Activating Token Index: 578