Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1971 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.4003. Min Act: -0.0000

Data Index: 1155983 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.4561. Min Act: -0.0000

Data Index: 480783 (The Pile)

Max Activating Token Index: 178

Text #2

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3649. Min Act: -0.0000

Data Index: 906762 (The Pile)

Max Activating Token Index: 863

Text #3

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3475. Min Act: -0.0000

Data Index: 888420 (The Pile)

Max Activating Token Index: 944

Text #4

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1453721 (The Pile)

Max Activating Token Index: 420

Text #5

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3611. Min Act: -0.0000

Data Index: 349123 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1585661 (The Pile)

Max Activating Token Index: 989

Text #7

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1979332 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1050008 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1386620 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3214. Min Act: -0.0000

Data Index: 1090660 (The Pile)

Max Activating Token Index: 995

Text #11

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3104. Min Act: -0.0000

Data Index: 448942 (The Pile)

Max Activating Token Index: 758

Text #12

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3030. Min Act: -0.0000

Data Index: 910183 (The Pile)

Max Activating Token Index: 963

Text #13

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2777. Min Act: -0.0000

Data Index: 819477 (The Pile)

Max Activating Token Index: 528

Text #14

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3074. Min Act: -0.0000

Data Index: 103086 (The Pile)

Max Activating Token Index: 996

Text #15

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1567719 (The Pile)

Max Activating Token Index: 1013

Text #16

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2739. Min Act: -0.0000

Data Index: 707580 (The Pile)

Max Activating Token Index: 834

Text #17

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1877523 (The Pile)

Max Activating Token Index: 986

Text #18

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1708790 (The Pile)

Max Activating Token Index: 981

Text #19

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2687. Min Act: -0.0000

Data Index: 472380 (The Pile)

Max Activating Token Index: 733