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

Dataset: The Pile

Neuron 1330 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1677748 (The Pile)

Max Activating Token Index: 446

Text #1

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3332. Min Act: -0.0000

Data Index: 668969 (The Pile)

Max Activating Token Index: 701

Text #2

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1430326 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1277018 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3197. Min Act: -0.0000

Data Index: 250796 (The Pile)

Max Activating Token Index: 506

Text #5

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2979. Min Act: -0.0000

Data Index: 408532 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2968. Min Act: -0.0000

Data Index: 272386 (The Pile)

Max Activating Token Index: 707

Text #7

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2956. Min Act: -0.0000

Data Index: 62055 (The Pile)

Max Activating Token Index: 916

Text #8

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3026. Min Act: 0.0000

Data Index: 727784 (The Pile)

Max Activating Token Index: 248

Text #9

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1087803 (The Pile)

Max Activating Token Index: 663

Text #10

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3033. Min Act: -0.0000

Data Index: 736213 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2851. Min Act: -0.0000

Data Index: 1438970 (The Pile)

Max Activating Token Index: 675

Text #12

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2831. Min Act: -0.0000

Data Index: 44597 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3040. Min Act: -0.0000

Data Index: 761450 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2661. Min Act: 0.0000

Data Index: 878677 (The Pile)

Max Activating Token Index: 800

Text #15

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2779. Min Act: -0.0000

Data Index: 140185 (The Pile)

Max Activating Token Index: 64

Text #16

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2774. Min Act: -0.0000

Data Index: 907146 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2749. Min Act: -0.0000

Data Index: 234979 (The Pile)

Max Activating Token Index: 117

Text #18

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1982528 (The Pile)

Max Activating Token Index: 226

Text #19

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1181481 (The Pile)

Max Activating Token Index: 655