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

Dataset: The Pile

Neuron 945 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.8968. Min Act: -0.0000

Data Index: 1464464 (The Pile)

Max Activating Token Index: 331

Text #1

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7814. Min Act: -0.0000

Data Index: 74365 (The Pile)

Max Activating Token Index: 126

Text #2

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7120. Min Act: -0.0000

Data Index: 402148 (The Pile)

Max Activating Token Index: 526

Text #3

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7059. Min Act: -0.0000

Data Index: 731519 (The Pile)

Max Activating Token Index: 335

Text #4

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7329. Min Act: -0.0000

Data Index: 952698 (The Pile)

Max Activating Token Index: 302

Text #5

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7121. Min Act: -0.0000

Data Index: 903491 (The Pile)

Max Activating Token Index: 877

Text #6

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.5977. Min Act: -0.0000

Data Index: 930068 (The Pile)

Max Activating Token Index: 718

Text #7

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7830. Min Act: -0.0000

Data Index: 1775638 (The Pile)

Max Activating Token Index: 813

Text #8

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1685219 (The Pile)

Max Activating Token Index: 933

Text #9

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6744. Min Act: -0.0000

Data Index: 144193 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6984. Min Act: -0.0000

Data Index: 40769 (The Pile)

Max Activating Token Index: 256

Text #11

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6871. Min Act: -0.0000

Data Index: 956192 (The Pile)

Max Activating Token Index: 886

Text #12

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7250. Min Act: -0.0000

Data Index: 600667 (The Pile)

Max Activating Token Index: 812

Text #13

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1028417 (The Pile)

Max Activating Token Index: 694

Text #14

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6740. Min Act: -0.0000

Data Index: 1714642 (The Pile)

Max Activating Token Index: 439

Text #15

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1320098 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6276. Min Act: -0.0000

Data Index: 951722 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1482420 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.5980. Min Act: -0.0000

Data Index: 7541 (The Pile)

Max Activating Token Index: 961

Text #19

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1516496 (The Pile)

Max Activating Token Index: 694