Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2857 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1317766 (The Pile)

Max Activating Token Index: 793

Text #1

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3968. Min Act: -0.0000

Data Index: 199821 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3966. Min Act: -0.0001

Data Index: 963437 (The Pile)

Max Activating Token Index: 497

Text #3

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1836286 (The Pile)

Max Activating Token Index: 721

Text #4

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3822. Min Act: -0.0000

Data Index: 554734 (The Pile)

Max Activating Token Index: 720

Text #5

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3772. Min Act: -0.0000

Data Index: 648315 (The Pile)

Max Activating Token Index: 931

Text #6

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1458965 (The Pile)

Max Activating Token Index: 802

Text #7

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3689. Min Act: -0.0000

Data Index: 195752 (The Pile)

Max Activating Token Index: 440

Text #8

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3544. Min Act: -0.0001

Data Index: 805465 (The Pile)

Max Activating Token Index: 682

Text #9

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1223408 (The Pile)

Max Activating Token Index: 834

Text #10

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.2914. Min Act: -0.0000

Data Index: 635573 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3440. Min Act: -0.0001

Data Index: 1506792 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3215. Min Act: -0.0001

Data Index: 1116102 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1662629 (The Pile)

Max Activating Token Index: 420

Text #14

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.2609. Min Act: -0.0000

Data Index: 274126 (The Pile)

Max Activating Token Index: 948

Text #15

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3214. Min Act: -0.0000

Data Index: 1255724 (The Pile)

Max Activating Token Index: 193

Text #16

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3305. Min Act: -0.0000

Data Index: 43401 (The Pile)

Max Activating Token Index: 664

Text #17

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3070. Min Act: -0.0000

Data Index: 1316287 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.2862. Min Act: -0.0000

Data Index: 121858 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 0.4828. Min Range: -0.4828

Max Act: 0.3380. Min Act: -0.0001

Data Index: 1719036 (The Pile)

Max Activating Token Index: 765