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

Dataset: The Pile

Neuron 4840 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: 0.3541. Min Range: -0.3541

Max Act: 0.3418. Min Act: -0.0000

Data Index: 450953 (The Pile)

Max Activating Token Index: 921

Text #1

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1882488 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3400. Min Act: -0.0000

Data Index: 121821 (The Pile)

Max Activating Token Index: 465

Text #3

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1864777 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3167. Min Act: -0.0000

Data Index: 877329 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1576174 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1462085 (The Pile)

Max Activating Token Index: 102

Text #7

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1506601 (The Pile)

Max Activating Token Index: 175

Text #8

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1030704 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3085. Min Act: -0.0000

Data Index: 709954 (The Pile)

Max Activating Token Index: 122

Text #10

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1809282 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3126. Min Act: -0.0000

Data Index: 1823249 (The Pile)

Max Activating Token Index: 176

Text #12

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1868546 (The Pile)

Max Activating Token Index: 637

Text #13

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2923. Min Act: -0.0000

Data Index: 274625 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1066007 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3028. Min Act: -0.0000

Data Index: 645603 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2928. Min Act: -0.0000

Data Index: 569037 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1974330 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2983. Min Act: 0.0000

Data Index: 331635 (The Pile)

Max Activating Token Index: 952

Text #19

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2858. Min Act: -0.0000

Data Index: 245723 (The Pile)

Max Activating Token Index: 498