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

Dataset: The Pile

Neuron 3327 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: 1.3759. Min Range: -1.3759

Max Act: 1.3759. Min Act: -0.0000

Data Index: 908224 (The Pile)

Max Activating Token Index: 480

Text #1

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1937. Min Act: -0.0000

Data Index: 1124580 (The Pile)

Max Activating Token Index: 358

Text #2

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.3105. Min Act: -0.0000

Data Index: 1280474 (The Pile)

Max Activating Token Index: 476

Text #3

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1875. Min Act: -0.0000

Data Index: 1589249 (The Pile)

Max Activating Token Index: 224

Text #4

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1978. Min Act: -0.0000

Data Index: 283656 (The Pile)

Max Activating Token Index: 77

Text #5

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1858237 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1857. Min Act: -0.0000

Data Index: 423326 (The Pile)

Max Activating Token Index: 753

Text #7

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.2043. Min Act: -0.0000

Data Index: 1820542 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1299. Min Act: -0.0000

Data Index: 305789 (The Pile)

Max Activating Token Index: 11

Text #9

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1303. Min Act: -0.0000

Data Index: 536282 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1776016 (The Pile)

Max Activating Token Index: 105

Text #11

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1889. Min Act: -0.0000

Data Index: 582836 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0886. Min Act: -0.0000

Data Index: 877413 (The Pile)

Max Activating Token Index: 172

Text #13

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0271. Min Act: -0.0000

Data Index: 1403555 (The Pile)

Max Activating Token Index: 988

Text #14

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1330. Min Act: -0.0000

Data Index: 271585 (The Pile)

Max Activating Token Index: 42

Text #15

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1001. Min Act: -0.0000

Data Index: 375912 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1334. Min Act: -0.0000

Data Index: 1004715 (The Pile)

Max Activating Token Index: 208

Text #17

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0855. Min Act: -0.0000

Data Index: 1718134 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1192. Min Act: -0.0000

Data Index: 919945 (The Pile)

Max Activating Token Index: 67

Text #19

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0217. Min Act: -0.0000

Data Index: 158460 (The Pile)

Max Activating Token Index: 429