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

Dataset: The Pile

Neuron 872 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: 0.8212. Min Range: -0.8212

Max Act: 0.8034. Min Act: -0.0000

Data Index: 1834853 (The Pile)

Max Activating Token Index: 478

Text #1

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1140258 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1766094 (The Pile)

Max Activating Token Index: 567

Text #3

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.7848. Min Act: -0.0000

Data Index: 1730073 (The Pile)

Max Activating Token Index: 517

Text #4

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6868. Min Act: -0.0000

Data Index: 689818 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1242131 (The Pile)

Max Activating Token Index: 123

Text #6

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.7484. Min Act: -0.0000

Data Index: 1029716 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1563696 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.7108. Min Act: -0.0000

Data Index: 372910 (The Pile)

Max Activating Token Index: 881

Text #9

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.7722. Min Act: -0.0000

Data Index: 40028 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1640119 (The Pile)

Max Activating Token Index: 594

Text #11

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1283449 (The Pile)

Max Activating Token Index: 379

Text #12

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1658642 (The Pile)

Max Activating Token Index: 836

Text #13

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1266606 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.7149. Min Act: -0.0000

Data Index: 275948 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1112254 (The Pile)

Max Activating Token Index: 148

Text #16

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1645523 (The Pile)

Max Activating Token Index: 224

Text #17

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6587. Min Act: -0.0000

Data Index: 254496 (The Pile)

Max Activating Token Index: 732

Text #18

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.7031. Min Act: -0.0000

Data Index: 91142 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6342. Min Act: -0.0000

Data Index: 1254838 (The Pile)

Max Activating Token Index: 919