Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3256 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1789482 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1527106 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1383789 (The Pile)

Max Activating Token Index: 786

Text #3

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3807. Min Act: -0.0000

Data Index: 434345 (The Pile)

Max Activating Token Index: 343

Text #4

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3569. Min Act: -0.0000

Data Index: 1547691 (The Pile)

Max Activating Token Index: 329

Text #5

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1395446 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1117789 (The Pile)

Max Activating Token Index: 364

Text #7

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3315. Min Act: -0.0000

Data Index: 1705550 (The Pile)

Max Activating Token Index: 24

Text #8

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1713195 (The Pile)

Max Activating Token Index: 821

Text #9

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1798189 (The Pile)

Max Activating Token Index: 779

Text #10

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1838098 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3125. Min Act: -0.0000

Data Index: 296937 (The Pile)

Max Activating Token Index: 950

Text #12

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3257. Min Act: -0.0000

Data Index: 125590 (The Pile)

Max Activating Token Index: 832

Text #13

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3218. Min Act: -0.0000

Data Index: 406940 (The Pile)

Max Activating Token Index: 550

Text #14

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3113. Min Act: -0.0000

Data Index: 43203 (The Pile)

Max Activating Token Index: 912

Text #15

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1850069 (The Pile)

Max Activating Token Index: 651

Text #16

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1004521 (The Pile)

Max Activating Token Index: 520

Text #17

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2933. Min Act: -0.0000

Data Index: 407662 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1619672 (The Pile)

Max Activating Token Index: 754

Text #19

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3062. Min Act: -0.0000

Data Index: 887210 (The Pile)

Max Activating Token Index: 903