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

Dataset: The Pile

Neuron 361 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.7764. Min Act: -0.0000

Data Index: 341415 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.6164. Min Act: -0.0000

Data Index: 960398 (The Pile)

Max Activating Token Index: 246

Text #2

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.7536. Min Act: -0.0000

Data Index: 607566 (The Pile)

Max Activating Token Index: 231

Text #3

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.7222. Min Act: -0.0000

Data Index: 797950 (The Pile)

Max Activating Token Index: 985

Text #4

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.7660. Min Act: -0.0000

Data Index: 1350555 (The Pile)

Max Activating Token Index: 748

Text #5

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.6010. Min Act: -0.0000

Data Index: 1410807 (The Pile)

Max Activating Token Index: 103

Text #6

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.6502. Min Act: -0.0000

Data Index: 218212 (The Pile)

Max Activating Token Index: 499

Text #7

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.6382. Min Act: -0.0000

Data Index: 1042794 (The Pile)

Max Activating Token Index: 725

Text #8

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.5842. Min Act: -0.0000

Data Index: 510557 (The Pile)

Max Activating Token Index: 325

Text #9

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.5810. Min Act: -0.0000

Data Index: 1834928 (The Pile)

Max Activating Token Index: 312

Text #10

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.6917. Min Act: -0.0000

Data Index: 1850891 (The Pile)

Max Activating Token Index: 535

Text #11

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.6195. Min Act: -0.0000

Data Index: 303998 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.5611. Min Act: -0.0000

Data Index: 120743 (The Pile)

Max Activating Token Index: 56

Text #13

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.6159. Min Act: -0.0000

Data Index: 1265116 (The Pile)

Max Activating Token Index: 137

Text #14

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.6470. Min Act: -0.0000

Data Index: 618519 (The Pile)

Max Activating Token Index: 406

Text #15

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.5513. Min Act: -0.0000

Data Index: 1127446 (The Pile)

Max Activating Token Index: 203

Text #16

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.4913. Min Act: -0.0000

Data Index: 363138 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.5959. Min Act: -0.0000

Data Index: 518652 (The Pile)

Max Activating Token Index: 76

Text #18

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.6146. Min Act: -0.0000

Data Index: 417239 (The Pile)

Max Activating Token Index: 97

Text #19

Max Range: 1.7764. Min Range: -1.7764

Max Act: 1.6500. Min Act: -0.0000

Data Index: 1006352 (The Pile)

Max Activating Token Index: 736