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

Dataset: The Pile

Neuron 4613 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.9977. Min Act: -0.0000

Data Index: 1976340 (The Pile)

Max Activating Token Index: 404

Text #1

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1580984 (The Pile)

Max Activating Token Index: 652

Text #2

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1859430 (The Pile)

Max Activating Token Index: 627

Text #3

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.6667. Min Act: -0.0000

Data Index: 596633 (The Pile)

Max Activating Token Index: 74

Text #4

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.7048. Min Act: -0.0000

Data Index: 697330 (The Pile)

Max Activating Token Index: 684

Text #5

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1970 (The Pile)

Max Activating Token Index: 372

Text #6

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.7275. Min Act: -0.0000

Data Index: 902128 (The Pile)

Max Activating Token Index: 455

Text #7

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.6442. Min Act: -0.0000

Data Index: 780834 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1592724 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.5887. Min Act: -0.0000

Data Index: 845530 (The Pile)

Max Activating Token Index: 303

Text #10

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1519248 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1500212 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1154959 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1907627 (The Pile)

Max Activating Token Index: 444

Text #14

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.5733. Min Act: -0.0000

Data Index: 676965 (The Pile)

Max Activating Token Index: 433

Text #15

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1946821 (The Pile)

Max Activating Token Index: 615

Text #16

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.5705. Min Act: -0.0000

Data Index: 1737871 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1919309 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1793531 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.5038. Min Act: -0.0000

Data Index: 290558 (The Pile)

Max Activating Token Index: 1023