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

Dataset: The Pile

Neuron 832 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: 0.3137. Min Range: -0.3137

Max Act: 0.3137. Min Act: -0.0000

Data Index: 1519429 (The Pile)

Max Activating Token Index: 213

Text #1

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.3036. Min Act: -0.0000

Data Index: 403696 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1448427 (The Pile)

Max Activating Token Index: 896

Text #3

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1144312 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2427. Min Act: -0.0000

Data Index: 702134 (The Pile)

Max Activating Token Index: 754

Text #5

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2175. Min Act: -0.0000

Data Index: 264676 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1713766 (The Pile)

Max Activating Token Index: 417

Text #7

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1115463 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1523253 (The Pile)

Max Activating Token Index: 194

Text #9

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1284618 (The Pile)

Max Activating Token Index: 479

Text #10

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.1933. Min Act: -0.0000

Data Index: 1937789 (The Pile)

Max Activating Token Index: 563

Text #11

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2045. Min Act: -0.0000

Data Index: 856165 (The Pile)

Max Activating Token Index: 163

Text #12

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.1869. Min Act: -0.0000

Data Index: 885916 (The Pile)

Max Activating Token Index: 733

Text #13

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2017. Min Act: -0.0000

Data Index: 424475 (The Pile)

Max Activating Token Index: 246

Text #14

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1279114 (The Pile)

Max Activating Token Index: 200

Text #15

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1884354 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2007. Min Act: -0.0000

Data Index: 107566 (The Pile)

Max Activating Token Index: 370

Text #17

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.1655. Min Act: -0.0000

Data Index: 1910045 (The Pile)

Max Activating Token Index: 747

Text #18

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1606902 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.1675. Min Act: -0.0000

Data Index: 1313566 (The Pile)

Max Activating Token Index: 124