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

Dataset: The Pile

Neuron 249 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: 0.5377. Min Range: -0.5377

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1775257 (The Pile)

Max Activating Token Index: 619

Text #1

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1427967 (The Pile)

Max Activating Token Index: 741

Text #2

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4098. Min Act: -0.0000

Data Index: 818648 (The Pile)

Max Activating Token Index: 710

Text #3

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1752158 (The Pile)

Max Activating Token Index: 853

Text #4

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1641152 (The Pile)

Max Activating Token Index: 375

Text #5

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3912. Min Act: -0.0000

Data Index: 1808089 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3639. Min Act: -0.0000

Data Index: 975200 (The Pile)

Max Activating Token Index: 370

Text #7

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3429. Min Act: -0.0000

Data Index: 485464 (The Pile)

Max Activating Token Index: 615

Text #8

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1955580 (The Pile)

Max Activating Token Index: 600

Text #9

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3248. Min Act: -0.0000

Data Index: 531751 (The Pile)

Max Activating Token Index: 508

Text #10

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.3037. Min Act: -0.0000

Data Index: 853063 (The Pile)

Max Activating Token Index: 787

Text #11

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.2888. Min Act: -0.0000

Data Index: 354977 (The Pile)

Max Activating Token Index: 914

Text #12

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.2855. Min Act: -0.0000

Data Index: 895089 (The Pile)

Max Activating Token Index: 941

Text #13

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1853869 (The Pile)

Max Activating Token Index: 949

Text #14

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.2899. Min Act: -0.0000

Data Index: 386450 (The Pile)

Max Activating Token Index: 956

Text #15

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1355533 (The Pile)

Max Activating Token Index: 586

Text #16

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.2652. Min Act: -0.0000

Data Index: 171199 (The Pile)

Max Activating Token Index: 427

Text #17

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1649198 (The Pile)

Max Activating Token Index: 670

Text #18

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1541104 (The Pile)

Max Activating Token Index: 394

Text #19

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.2731. Min Act: -0.0000

Data Index: 951200 (The Pile)

Max Activating Token Index: 942