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

Dataset: The Pile

Neuron 2423 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: 0.3430. Min Range: -0.3430

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1885124 (The Pile)

Max Activating Token Index: 100

Text #1

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1658474 (The Pile)

Max Activating Token Index: 926

Text #2

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.3160. Min Act: -0.0000

Data Index: 70309 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2785. Min Act: -0.0000

Data Index: 265943 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2745. Min Act: -0.0000

Data Index: 576212 (The Pile)

Max Activating Token Index: 765

Text #5

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2937. Min Act: -0.0000

Data Index: 1790689 (The Pile)

Max Activating Token Index: 194

Text #6

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2742. Min Act: -0.0000

Data Index: 224362 (The Pile)

Max Activating Token Index: 837

Text #7

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2871. Min Act: -0.0000

Data Index: 1989209 (The Pile)

Max Activating Token Index: 807

Text #8

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2746. Min Act: -0.0000

Data Index: 1233296 (The Pile)

Max Activating Token Index: 812

Text #9

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1720563 (The Pile)

Max Activating Token Index: 939

Text #10

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1456962 (The Pile)

Max Activating Token Index: 335

Text #11

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2718. Min Act: -0.0000

Data Index: 220145 (The Pile)

Max Activating Token Index: 68

Text #12

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2683. Min Act: -0.0000

Data Index: 930441 (The Pile)

Max Activating Token Index: 435

Text #13

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1976340 (The Pile)

Max Activating Token Index: 92

Text #14

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1069369 (The Pile)

Max Activating Token Index: 325

Text #15

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1257944 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1183857 (The Pile)

Max Activating Token Index: 801

Text #17

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1080493 (The Pile)

Max Activating Token Index: 576

Text #18

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2700. Min Act: -0.0000

Data Index: 821698 (The Pile)

Max Activating Token Index: 97

Text #19

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1500300 (The Pile)

Max Activating Token Index: 10