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

Dataset: The Pile

Neuron 3982 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3239. Min Range: -1.3239

Max Act: 1.3239. Min Act: -0.0000

Data Index: 1993703 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 1.3239. Min Range: -1.3239

Max Act: 1.1051. Min Act: -0.0000

Data Index: 482136 (The Pile)

Max Activating Token Index: 693

Text #2

Max Range: 1.3239. Min Range: -1.3239

Max Act: 1.2363. Min Act: -0.0000

Data Index: 859217 (The Pile)

Max Activating Token Index: 872

Text #3

Max Range: 1.3239. Min Range: -1.3239

Max Act: 1.1613. Min Act: -0.0000

Data Index: 51527 (The Pile)

Max Activating Token Index: 437

Text #4

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.8528. Min Act: -0.0000

Data Index: 1807396 (The Pile)

Max Activating Token Index: 450

Text #5

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.8272. Min Act: -0.0000

Data Index: 51009 (The Pile)

Max Activating Token Index: 226

Text #6

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.8779. Min Act: -0.0000

Data Index: 1486597 (The Pile)

Max Activating Token Index: 189

Text #7

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.7344. Min Act: -0.0000

Data Index: 1927418 (The Pile)

Max Activating Token Index: 1007

Text #8

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.8153. Min Act: -0.0000

Data Index: 1828216 (The Pile)

Max Activating Token Index: 453

Text #9

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.8327. Min Act: -0.0000

Data Index: 172950 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1056369 (The Pile)

Max Activating Token Index: 221

Text #11

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1858919 (The Pile)

Max Activating Token Index: 71

Text #12

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1221729 (The Pile)

Max Activating Token Index: 266

Text #13

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.8507. Min Act: -0.0000

Data Index: 960750 (The Pile)

Max Activating Token Index: 163

Text #14

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.7641. Min Act: -0.0000

Data Index: 957694 (The Pile)

Max Activating Token Index: 243

Text #15

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1152684 (The Pile)

Max Activating Token Index: 653

Text #16

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1516148 (The Pile)

Max Activating Token Index: 895

Text #17

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.7536. Min Act: -0.0000

Data Index: 921382 (The Pile)

Max Activating Token Index: 932

Text #18

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.6949. Min Act: -0.0000

Data Index: 964131 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1769617 (The Pile)

Max Activating Token Index: 487