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

Dataset: The Pile

Neuron 2557 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: 1.5586. Min Range: -1.5586

Max Act: 1.5586. Min Act: -0.0000

Data Index: 1573782 (The Pile)

Max Activating Token Index: 940

Text #1

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.3632. Min Act: -0.0000

Data Index: 1791548 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.3879. Min Act: -0.0000

Data Index: 193035 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.2508. Min Act: -0.0000

Data Index: 352553 (The Pile)

Max Activating Token Index: 68

Text #4

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.4039. Min Act: -0.0000

Data Index: 1053379 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.2196. Min Act: -0.0000

Data Index: 528000 (The Pile)

Max Activating Token Index: 886

Text #6

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.2309. Min Act: -0.0000

Data Index: 76326 (The Pile)

Max Activating Token Index: 302

Text #7

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.1564. Min Act: -0.0000

Data Index: 1105987 (The Pile)

Max Activating Token Index: 309

Text #8

Max Range: 1.5586. Min Range: -1.5586

Max Act: 0.9734. Min Act: -0.0000

Data Index: 1846501 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.1456. Min Act: -0.0000

Data Index: 707562 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.3771. Min Act: -0.0000

Data Index: 1432214 (The Pile)

Max Activating Token Index: 966

Text #11

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.0199. Min Act: -0.0000

Data Index: 908635 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.1178. Min Act: -0.0000

Data Index: 376188 (The Pile)

Max Activating Token Index: 962

Text #13

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.1527. Min Act: -0.0000

Data Index: 483731 (The Pile)

Max Activating Token Index: 170

Text #14

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.0647. Min Act: -0.0000

Data Index: 27615 (The Pile)

Max Activating Token Index: 66

Text #15

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1166640 (The Pile)

Max Activating Token Index: 313

Text #16

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1617467 (The Pile)

Max Activating Token Index: 968

Text #17

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.0254. Min Act: -0.0000

Data Index: 322742 (The Pile)

Max Activating Token Index: 913

Text #18

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.0137. Min Act: -0.0000

Data Index: 383666 (The Pile)

Max Activating Token Index: 950

Text #19

Max Range: 1.5586. Min Range: -1.5586

Max Act: 0.9593. Min Act: -0.0000

Data Index: 997615 (The Pile)

Max Activating Token Index: 885