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

Dataset: The Pile

Neuron 3647 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1765. Min Range: -1.1765

Max Act: 1.1765. Min Act: -0.0000

Data Index: 1579587 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 1.1765. Min Range: -1.1765

Max Act: 1.1519. Min Act: -0.0000

Data Index: 1236632 (The Pile)

Max Activating Token Index: 72

Text #2

Max Range: 1.1765. Min Range: -1.1765

Max Act: 1.0290. Min Act: -0.0000

Data Index: 1177877 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 1.1765. Min Range: -1.1765

Max Act: 1.0084. Min Act: -0.0000

Data Index: 543190 (The Pile)

Max Activating Token Index: 148

Text #4

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.9333. Min Act: -0.0000

Data Index: 800339 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.9125. Min Act: -0.0000

Data Index: 279564 (The Pile)

Max Activating Token Index: 634

Text #6

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.9125. Min Act: -0.0000

Data Index: 1056345 (The Pile)

Max Activating Token Index: 228

Text #7

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.9431. Min Act: -0.0000

Data Index: 772167 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.8532. Min Act: -0.0000

Data Index: 551996 (The Pile)

Max Activating Token Index: 151

Text #9

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.8102. Min Act: -0.0000

Data Index: 197972 (The Pile)

Max Activating Token Index: 539

Text #10

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1391661 (The Pile)

Max Activating Token Index: 392

Text #11

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.8210. Min Act: -0.0000

Data Index: 1035483 (The Pile)

Max Activating Token Index: 38

Text #12

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1824185 (The Pile)

Max Activating Token Index: 130

Text #13

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.9127. Min Act: -0.0000

Data Index: 974396 (The Pile)

Max Activating Token Index: 785

Text #14

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1314727 (The Pile)

Max Activating Token Index: 53

Text #15

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1524151 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.7958. Min Act: -0.0000

Data Index: 394674 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.8152. Min Act: -0.0000

Data Index: 536686 (The Pile)

Max Activating Token Index: 799

Text #18

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.8233. Min Act: -0.0000

Data Index: 354250 (The Pile)

Max Activating Token Index: 174

Text #19

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.8737. Min Act: -0.0000

Data Index: 1715222 (The Pile)

Max Activating Token Index: 832