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

Dataset: The Pile

Neuron 3488 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: 1.0284. Min Range: -1.0284

Max Act: 1.0284. Min Act: -0.0000

Data Index: 1105931 (The Pile)

Max Activating Token Index: 344

Text #1

Max Range: 1.0284. Min Range: -1.0284

Max Act: 1.0111. Min Act: -0.0000

Data Index: 222386 (The Pile)

Max Activating Token Index: 1012

Text #2

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.9183. Min Act: -0.0000

Data Index: 1825974 (The Pile)

Max Activating Token Index: 90

Text #3

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.9207. Min Act: -0.0000

Data Index: 1937179 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1031837 (The Pile)

Max Activating Token Index: 549

Text #5

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.9084. Min Act: -0.0000

Data Index: 107792 (The Pile)

Max Activating Token Index: 395

Text #6

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8437. Min Act: -0.0000

Data Index: 881595 (The Pile)

Max Activating Token Index: 938

Text #7

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8990. Min Act: -0.0000

Data Index: 269243 (The Pile)

Max Activating Token Index: 184

Text #8

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8208. Min Act: -0.0000

Data Index: 854756 (The Pile)

Max Activating Token Index: 113

Text #9

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8106. Min Act: -0.0000

Data Index: 112522 (The Pile)

Max Activating Token Index: 119

Text #10

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.9038. Min Act: -0.0000

Data Index: 974226 (The Pile)

Max Activating Token Index: 816

Text #11

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8577. Min Act: -0.0000

Data Index: 1926868 (The Pile)

Max Activating Token Index: 753

Text #12

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1814836 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1704610 (The Pile)

Max Activating Token Index: 1000

Text #14

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1336992 (The Pile)

Max Activating Token Index: 108

Text #15

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1107410 (The Pile)

Max Activating Token Index: 458

Text #16

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1105160 (The Pile)

Max Activating Token Index: 223

Text #17

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.7690. Min Act: -0.0000

Data Index: 440398 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.7802. Min Act: 0.0000

Data Index: 458206 (The Pile)

Max Activating Token Index: 288

Text #19

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1449019 (The Pile)

Max Activating Token Index: 201