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

Dataset: The Pile

Neuron 1202 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: 0.7945. Min Range: -0.7945

Max Act: 0.7945. Min Act: -0.0000

Data Index: 478083 (The Pile)

Max Activating Token Index: 970

Text #1

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1834744 (The Pile)

Max Activating Token Index: 789

Text #2

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6666. Min Act: -0.0000

Data Index: 226611 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1349871 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6417. Min Act: -0.0000

Data Index: 745135 (The Pile)

Max Activating Token Index: 59

Text #5

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6596. Min Act: -0.0000

Data Index: 995057 (The Pile)

Max Activating Token Index: 220

Text #6

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6040. Min Act: -0.0000

Data Index: 755233 (The Pile)

Max Activating Token Index: 691

Text #7

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6109. Min Act: -0.0000

Data Index: 639386 (The Pile)

Max Activating Token Index: 994

Text #8

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6196. Min Act: -0.0000

Data Index: 961977 (The Pile)

Max Activating Token Index: 607

Text #9

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5868. Min Act: -0.0000

Data Index: 540658 (The Pile)

Max Activating Token Index: 387

Text #10

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5565. Min Act: -0.0000

Data Index: 485422 (The Pile)

Max Activating Token Index: 327

Text #11

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1016130 (The Pile)

Max Activating Token Index: 304

Text #12

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5674. Min Act: -0.0000

Data Index: 871203 (The Pile)

Max Activating Token Index: 636

Text #13

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1498864 (The Pile)

Max Activating Token Index: 291

Text #14

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1068614 (The Pile)

Max Activating Token Index: 201

Text #15

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5057. Min Act: -0.0000

Data Index: 503483 (The Pile)

Max Activating Token Index: 594

Text #16

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5548. Min Act: -0.0000

Data Index: 798992 (The Pile)

Max Activating Token Index: 427

Text #17

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5609. Min Act: -0.0000

Data Index: 224848 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.4996. Min Act: -0.0000

Data Index: 367770 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5337. Min Act: -0.0000

Data Index: 213023 (The Pile)

Max Activating Token Index: 211