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

Dataset: The Pile

Neuron 4411 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1015901 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1584669 (The Pile)

Max Activating Token Index: 102

Text #2

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6244. Min Act: -0.0000

Data Index: 748314 (The Pile)

Max Activating Token Index: 763

Text #3

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1885998 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1017514 (The Pile)

Max Activating Token Index: 797

Text #5

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.8069. Min Act: -0.0000

Data Index: 193116 (The Pile)

Max Activating Token Index: 798

Text #6

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1033834 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6485. Min Act: -0.0000

Data Index: 500958 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1389294 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5768. Min Act: -0.0000

Data Index: 529225 (The Pile)

Max Activating Token Index: 657

Text #10

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5565. Min Act: -0.0000

Data Index: 964555 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5055. Min Act: -0.0000

Data Index: 133738 (The Pile)

Max Activating Token Index: 83

Text #12

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1639929 (The Pile)

Max Activating Token Index: 378

Text #13

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5365. Min Act: -0.0000

Data Index: 91410 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1832791 (The Pile)

Max Activating Token Index: 442

Text #15

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1489095 (The Pile)

Max Activating Token Index: 174

Text #16

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1907239 (The Pile)

Max Activating Token Index: 621

Text #17

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5396. Min Act: -0.0000

Data Index: 326658 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1534490 (The Pile)

Max Activating Token Index: 406

Text #19

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1182083 (The Pile)

Max Activating Token Index: 690