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

Dataset: The Pile

Neuron 1506 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1882074 (The Pile)

Max Activating Token Index: 501

Text #1

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1810102 (The Pile)

Max Activating Token Index: 727

Text #2

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1490757 (The Pile)

Max Activating Token Index: 742

Text #3

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3693. Min Act: -0.0000

Data Index: 866664 (The Pile)

Max Activating Token Index: 220

Text #4

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3470. Min Act: -0.0000

Data Index: 836347 (The Pile)

Max Activating Token Index: 829

Text #5

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1990658 (The Pile)

Max Activating Token Index: 362

Text #6

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3406. Min Act: -0.0000

Data Index: 711855 (The Pile)

Max Activating Token Index: 472

Text #7

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3305. Min Act: -0.0000

Data Index: 386514 (The Pile)

Max Activating Token Index: 571

Text #8

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1066470 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3253. Min Act: -0.0000

Data Index: 98509 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3350. Min Act: -0.0000

Data Index: 750600 (The Pile)

Max Activating Token Index: 816

Text #11

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3194. Min Act: -0.0000

Data Index: 107590 (The Pile)

Max Activating Token Index: 424

Text #12

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1168988 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3143. Min Act: -0.0000

Data Index: 580974 (The Pile)

Max Activating Token Index: 752

Text #14

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1209087 (The Pile)

Max Activating Token Index: 276

Text #15

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3179. Min Act: -0.0000

Data Index: 845651 (The Pile)

Max Activating Token Index: 972

Text #16

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.2871. Min Act: -0.0000

Data Index: 1189822 (The Pile)

Max Activating Token Index: 407

Text #17

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3056. Min Act: -0.0000

Data Index: 378476 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1633078 (The Pile)

Max Activating Token Index: 677

Text #19

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1437582 (The Pile)

Max Activating Token Index: 337