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

Dataset: The Pile

Neuron 1436 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1697220 (The Pile)

Max Activating Token Index: 234

Text #1

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5923. Min Act: -0.0000

Data Index: 992011 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1988149 (The Pile)

Max Activating Token Index: 914

Text #3

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1869516 (The Pile)

Max Activating Token Index: 160

Text #4

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1621534 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6279. Min Act: -0.0000

Data Index: 418968 (The Pile)

Max Activating Token Index: 723

Text #6

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5457. Min Act: -0.0000

Data Index: 670739 (The Pile)

Max Activating Token Index: 131

Text #7

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1634331 (The Pile)

Max Activating Token Index: 245

Text #8

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6235. Min Act: -0.0000

Data Index: 99850 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1098582 (The Pile)

Max Activating Token Index: 893

Text #10

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6027. Min Act: -0.0000

Data Index: 443466 (The Pile)

Max Activating Token Index: 581

Text #11

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5574. Min Act: -0.0000

Data Index: 647801 (The Pile)

Max Activating Token Index: 616

Text #12

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1112768 (The Pile)

Max Activating Token Index: 514

Text #13

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1952211 (The Pile)

Max Activating Token Index: 732

Text #14

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6807. Min Act: -0.0000

Data Index: 161908 (The Pile)

Max Activating Token Index: 227

Text #15

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1850976 (The Pile)

Max Activating Token Index: 614

Text #16

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5783. Min Act: -0.0000

Data Index: 657202 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5161. Min Act: -0.0000

Data Index: 471599 (The Pile)

Max Activating Token Index: 61

Text #18

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5512. Min Act: -0.0000

Data Index: 753604 (The Pile)

Max Activating Token Index: 348

Text #19

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5514. Min Act: -0.0000

Data Index: 91719 (The Pile)

Max Activating Token Index: 194