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

Dataset: The Pile

Neuron 3084 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: 0.7979. Min Range: -0.7979

Max Act: 0.7924. Min Act: -0.0000

Data Index: 71062 (The Pile)

Max Activating Token Index: 303

Text #1

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1182912 (The Pile)

Max Activating Token Index: 525

Text #2

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.7765. Min Act: -0.0000

Data Index: 461788 (The Pile)

Max Activating Token Index: 298

Text #3

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.7406. Min Act: -0.0000

Data Index: 666291 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.7638. Min Act: -0.0000

Data Index: 944220 (The Pile)

Max Activating Token Index: 500

Text #5

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1037504 (The Pile)

Max Activating Token Index: 508

Text #6

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.6860. Min Act: 0.0000

Data Index: 1849832 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1420480 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1556210 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5668. Min Act: 0.0000

Data Index: 1121734 (The Pile)

Max Activating Token Index: 57

Text #10

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5869. Min Act: -0.0000

Data Index: 277559 (The Pile)

Max Activating Token Index: 263

Text #11

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5707. Min Act: -0.0000

Data Index: 625488 (The Pile)

Max Activating Token Index: 316

Text #12

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1958994 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.4935. Min Act: -0.0000

Data Index: 407858 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5159. Min Act: -0.0000

Data Index: 281964 (The Pile)

Max Activating Token Index: 272

Text #15

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.4976. Min Act: 0.0000

Data Index: 735930 (The Pile)

Max Activating Token Index: 587

Text #16

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1786324 (The Pile)

Max Activating Token Index: 561

Text #17

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1843629 (The Pile)

Max Activating Token Index: 717

Text #18

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.4892. Min Act: -0.0000

Data Index: 210644 (The Pile)

Max Activating Token Index: 977

Text #19

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5027. Min Act: -0.0000

Data Index: 945309 (The Pile)

Max Activating Token Index: 24