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

Dataset: The Pile

Neuron 4023 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1225. Min Range: -1.1225

Max Act: 1.1225. Min Act: -0.0000

Data Index: 695706 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 1.1225. Min Range: -1.1225

Max Act: 1.1077. Min Act: -0.0000

Data Index: 230075 (The Pile)

Max Activating Token Index: 276

Text #2

Max Range: 1.1225. Min Range: -1.1225

Max Act: 1.0331. Min Act: -0.0000

Data Index: 566166 (The Pile)

Max Activating Token Index: 229

Text #3

Max Range: 1.1225. Min Range: -1.1225

Max Act: 1.0281. Min Act: -0.0000

Data Index: 116227 (The Pile)

Max Activating Token Index: 572

Text #4

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1506984 (The Pile)

Max Activating Token Index: 805

Text #5

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.9064. Min Act: -0.0000

Data Index: 500405 (The Pile)

Max Activating Token Index: 156

Text #6

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1492433 (The Pile)

Max Activating Token Index: 822

Text #7

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8275. Min Act: -0.0000

Data Index: 56705 (The Pile)

Max Activating Token Index: 784

Text #8

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.9084. Min Act: -0.0000

Data Index: 569944 (The Pile)

Max Activating Token Index: 187

Text #9

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1451554 (The Pile)

Max Activating Token Index: 953

Text #10

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8466. Min Act: -0.0000

Data Index: 1571487 (The Pile)

Max Activating Token Index: 345

Text #11

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8109. Min Act: -0.0000

Data Index: 278964 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8624. Min Act: -0.0000

Data Index: 780366 (The Pile)

Max Activating Token Index: 172

Text #13

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8513. Min Act: -0.0000

Data Index: 1300748 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8670. Min Act: -0.0000

Data Index: 1868124 (The Pile)

Max Activating Token Index: 796

Text #15

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8339. Min Act: -0.0000

Data Index: 211860 (The Pile)

Max Activating Token Index: 97

Text #16

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1521859 (The Pile)

Max Activating Token Index: 320

Text #17

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1588749 (The Pile)

Max Activating Token Index: 633

Text #18

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.7849. Min Act: -0.0000

Data Index: 849976 (The Pile)

Max Activating Token Index: 816

Text #19

Max Range: 1.1225. Min Range: -1.1225

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1646032 (The Pile)

Max Activating Token Index: 340