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

Dataset: The Pile

Neuron 686 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: 0.7710. Min Range: -0.7710

Max Act: 0.7710. Min Act: -0.0000

Data Index: 1061261 (The Pile)

Max Activating Token Index: 969

Text #1

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1275930 (The Pile)

Max Activating Token Index: 299

Text #2

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1182767 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.3968. Min Act: -0.0000

Data Index: 950864 (The Pile)

Max Activating Token Index: 652

Text #4

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.4043. Min Act: -0.0000

Data Index: 100925 (The Pile)

Max Activating Token Index: 656

Text #5

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.3995. Min Act: -0.0000

Data Index: 1331370 (The Pile)

Max Activating Token Index: 678

Text #6

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1896596 (The Pile)

Max Activating Token Index: 990

Text #7

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1900272 (The Pile)

Max Activating Token Index: 979

Text #8

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.3301. Min Act: -0.0000

Data Index: 477015 (The Pile)

Max Activating Token Index: 896

Text #9

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.3698. Min Act: -0.0000

Data Index: 440676 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.3531. Min Act: -0.0000

Data Index: 490965 (The Pile)

Max Activating Token Index: 828

Text #11

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1297260 (The Pile)

Max Activating Token Index: 286

Text #12

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1600402 (The Pile)

Max Activating Token Index: 683

Text #13

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.3726. Min Act: -0.0000

Data Index: 902724 (The Pile)

Max Activating Token Index: 720

Text #14

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.3156. Min Act: -0.0000

Data Index: 922666 (The Pile)

Max Activating Token Index: 938

Text #15

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.3163. Min Act: -0.0000

Data Index: 291616 (The Pile)

Max Activating Token Index: 993

Text #16

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.3323. Min Act: -0.0000

Data Index: 147424 (The Pile)

Max Activating Token Index: 957

Text #17

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1749789 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.3129. Min Act: -0.0000

Data Index: 697408 (The Pile)

Max Activating Token Index: 839

Text #19

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.2990. Min Act: -0.0000

Data Index: 1193129 (The Pile)

Max Activating Token Index: 834