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

Dataset: The Pile

Neuron 3468 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: 1.2052. Min Range: -1.2052

Max Act: 1.2045. Min Act: -0.0000

Data Index: 1395482 (The Pile)

Max Activating Token Index: 252

Text #1

Max Range: 1.2052. Min Range: -1.2052

Max Act: 1.1844. Min Act: -0.0000

Data Index: 1413027 (The Pile)

Max Activating Token Index: 343

Text #2

Max Range: 1.2052. Min Range: -1.2052

Max Act: 1.2052. Min Act: -0.0000

Data Index: 235689 (The Pile)

Max Activating Token Index: 265

Text #3

Max Range: 1.2052. Min Range: -1.2052

Max Act: 1.0179. Min Act: -0.0000

Data Index: 711514 (The Pile)

Max Activating Token Index: 811

Text #4

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1139891 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1604494 (The Pile)

Max Activating Token Index: 649

Text #6

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1149151 (The Pile)

Max Activating Token Index: 365

Text #7

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.8195. Min Act: -0.0000

Data Index: 622315 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.8141. Min Act: -0.0000

Data Index: 574903 (The Pile)

Max Activating Token Index: 38

Text #9

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1419686 (The Pile)

Max Activating Token Index: 243

Text #10

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1414914 (The Pile)

Max Activating Token Index: 182

Text #11

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1447022 (The Pile)

Max Activating Token Index: 653

Text #12

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.7530. Min Act: -0.0000

Data Index: 143800 (The Pile)

Max Activating Token Index: 117

Text #13

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.7018. Min Act: -0.0000

Data Index: 362396 (The Pile)

Max Activating Token Index: 580

Text #14

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1632786 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.6910. Min Act: -0.0000

Data Index: 120573 (The Pile)

Max Activating Token Index: 909

Text #16

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1693910 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1906872 (The Pile)

Max Activating Token Index: 492

Text #18

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.7021. Min Act: -0.0000

Data Index: 1709905 (The Pile)

Max Activating Token Index: 300

Text #19

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.6804. Min Act: -0.0000

Data Index: 259177 (The Pile)

Max Activating Token Index: 576