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

Dataset: The Pile

Neuron 3142 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.5311. Min Act: -0.0000

Data Index: 221935 (The Pile)

Max Activating Token Index: 962

Text #1

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4653. Min Act: -0.0001

Data Index: 696866 (The Pile)

Max Activating Token Index: 960

Text #2

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1538026 (The Pile)

Max Activating Token Index: 706

Text #3

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1770847 (The Pile)

Max Activating Token Index: 798

Text #4

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4344. Min Act: -0.0000

Data Index: 391652 (The Pile)

Max Activating Token Index: 837

Text #5

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1260851 (The Pile)

Max Activating Token Index: 994

Text #6

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4341. Min Act: -0.0000

Data Index: 139497 (The Pile)

Max Activating Token Index: 899

Text #7

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4363. Min Act: -0.0000

Data Index: 749714 (The Pile)

Max Activating Token Index: 766

Text #8

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1132104 (The Pile)

Max Activating Token Index: 20

Text #9

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1198816 (The Pile)

Max Activating Token Index: 203

Text #10

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3884. Min Act: -0.0000

Data Index: 938387 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4022. Min Act: -0.0000

Data Index: 562059 (The Pile)

Max Activating Token Index: 906

Text #12

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1540598 (The Pile)

Max Activating Token Index: 13

Text #13

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1098790 (The Pile)

Max Activating Token Index: 630

Text #14

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3845. Min Act: -0.0000

Data Index: 911599 (The Pile)

Max Activating Token Index: 533

Text #15

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3795. Min Act: -0.0000

Data Index: 808524 (The Pile)

Max Activating Token Index: 243

Text #16

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3855. Min Act: -0.0000

Data Index: 486036 (The Pile)

Max Activating Token Index: 790

Text #17

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1038389 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1258711 (The Pile)

Max Activating Token Index: 256

Text #19

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1801109 (The Pile)

Max Activating Token Index: 273