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

Dataset: The Pile

Neuron 3657 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.6762. Min Act: -0.0000

Data Index: 841857 (The Pile)

Max Activating Token Index: 190

Text #1

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1147463 (The Pile)

Max Activating Token Index: 348

Text #2

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.6060. Min Act: -0.0000

Data Index: 1772783 (The Pile)

Max Activating Token Index: 271

Text #3

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5786. Min Act: 0.0000

Data Index: 996019 (The Pile)

Max Activating Token Index: 25

Text #4

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1919911 (The Pile)

Max Activating Token Index: 337

Text #5

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5252. Min Act: -0.0000

Data Index: 276978 (The Pile)

Max Activating Token Index: 646

Text #6

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5431. Min Act: -0.0000

Data Index: 320448 (The Pile)

Max Activating Token Index: 692

Text #7

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5149. Min Act: -0.0000

Data Index: 779719 (The Pile)

Max Activating Token Index: 1010

Text #8

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5509. Min Act: -0.0000

Data Index: 778414 (The Pile)

Max Activating Token Index: 512

Text #9

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1988722 (The Pile)

Max Activating Token Index: 576

Text #10

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5372. Min Act: -0.0000

Data Index: 532275 (The Pile)

Max Activating Token Index: 81

Text #11

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1428720 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5058. Min Act: -0.0000

Data Index: 582876 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5368. Min Act: 0.0000

Data Index: 78375 (The Pile)

Max Activating Token Index: 421

Text #14

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4976. Min Act: -0.0000

Data Index: 604554 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5118. Min Act: -0.0000

Data Index: 341900 (The Pile)

Max Activating Token Index: 284

Text #16

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4944. Min Act: -0.0000

Data Index: 472818 (The Pile)

Max Activating Token Index: 190

Text #17

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1040958 (The Pile)

Max Activating Token Index: 873

Text #18

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4906. Min Act: -0.0000

Data Index: 1768909 (The Pile)

Max Activating Token Index: 421

Text #19

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4873. Min Act: -0.0000

Data Index: 820629 (The Pile)

Max Activating Token Index: 854