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

Dataset: The Pile

Neuron 5076 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3827. Min Act: -0.0000

Data Index: 249962 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3273. Min Act: -0.0000

Data Index: 792480 (The Pile)

Max Activating Token Index: 106

Text #2

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3678. Min Act: -0.0000

Data Index: 305398 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3299. Min Act: -0.0000

Data Index: 120204 (The Pile)

Max Activating Token Index: 210

Text #4

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1532479 (The Pile)

Max Activating Token Index: 403

Text #5

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3713. Min Act: -0.0000

Data Index: 923580 (The Pile)

Max Activating Token Index: 825

Text #6

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3155. Min Act: -0.0000

Data Index: 1970653 (The Pile)

Max Activating Token Index: 611

Text #7

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1433619 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1183560 (The Pile)

Max Activating Token Index: 154

Text #9

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3160. Min Act: -0.0000

Data Index: 312731 (The Pile)

Max Activating Token Index: 691

Text #10

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3192. Min Act: -0.0000

Data Index: 824167 (The Pile)

Max Activating Token Index: 46

Text #11

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1528613 (The Pile)

Max Activating Token Index: 449

Text #12

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1149099 (The Pile)

Max Activating Token Index: 604

Text #13

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2807. Min Act: -0.0000

Data Index: 389905 (The Pile)

Max Activating Token Index: 667

Text #14

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1709267 (The Pile)

Max Activating Token Index: 560

Text #15

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2682. Min Act: -0.0000

Data Index: 1136370 (The Pile)

Max Activating Token Index: 532

Text #16

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2713. Min Act: -0.0000

Data Index: 381436 (The Pile)

Max Activating Token Index: 92

Text #17

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2884. Min Act: -0.0000

Data Index: 923738 (The Pile)

Max Activating Token Index: 617

Text #18

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1681405 (The Pile)

Max Activating Token Index: 165

Text #19

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1173053 (The Pile)

Max Activating Token Index: 840