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

Dataset: The Pile

Neuron 2488 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: 0.4482. Min Range: -0.4482

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1616425 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3418. Min Act: -0.0000

Data Index: 776881 (The Pile)

Max Activating Token Index: 721

Text #2

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3189. Min Act: -0.0000

Data Index: 965242 (The Pile)

Max Activating Token Index: 668

Text #3

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2930. Min Act: -0.0000

Data Index: 46699 (The Pile)

Max Activating Token Index: 853

Text #4

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2788. Min Act: -0.0000

Data Index: 1040369 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2786. Min Act: -0.0000

Data Index: 711078 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2724. Min Act: -0.0000

Data Index: 1683295 (The Pile)

Max Activating Token Index: 300

Text #7

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1679877 (The Pile)

Max Activating Token Index: 88

Text #8

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2693. Min Act: -0.0000

Data Index: 166131 (The Pile)

Max Activating Token Index: 154

Text #9

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2477. Min Act: -0.0000

Data Index: 945291 (The Pile)

Max Activating Token Index: 275

Text #10

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1097058 (The Pile)

Max Activating Token Index: 749

Text #11

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2315. Min Act: -0.0000

Data Index: 283635 (The Pile)

Max Activating Token Index: 212

Text #12

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1352410 (The Pile)

Max Activating Token Index: 893

Text #13

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1196604 (The Pile)

Max Activating Token Index: 332

Text #14

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2190. Min Act: -0.0000

Data Index: 514514 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2042. Min Act: -0.0000

Data Index: 336488 (The Pile)

Max Activating Token Index: 171

Text #16

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2166. Min Act: -0.0000

Data Index: 672862 (The Pile)

Max Activating Token Index: 828

Text #17

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1666675 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1764114 (The Pile)

Max Activating Token Index: 688

Text #19

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2127. Min Act: -0.0000

Data Index: 1818648 (The Pile)

Max Activating Token Index: 127