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

Dataset: The Pile

Neuron 3741 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.3136. Min Act: -0.0000

Data Index: 1306073 (The Pile)

Max Activating Token Index: 542

Text #1

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1333561 (The Pile)

Max Activating Token Index: 448

Text #2

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0506. Min Act: -0.0000

Data Index: 975813 (The Pile)

Max Activating Token Index: 303

Text #3

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.9687. Min Act: -0.0000

Data Index: 1022806 (The Pile)

Max Activating Token Index: 221

Text #4

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.1707. Min Act: -0.0000

Data Index: 1016415 (The Pile)

Max Activating Token Index: 851

Text #5

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.9405. Min Act: -0.0000

Data Index: 1608742 (The Pile)

Max Activating Token Index: 794

Text #6

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1378101 (The Pile)

Max Activating Token Index: 170

Text #7

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.9577. Min Act: -0.0000

Data Index: 662029 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.8546. Min Act: -0.0000

Data Index: 1864074 (The Pile)

Max Activating Token Index: 913

Text #9

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.8717. Min Act: -0.0000

Data Index: 598835 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.8639. Min Act: -0.0000

Data Index: 822834 (The Pile)

Max Activating Token Index: 146

Text #11

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.8024. Min Act: -0.0000

Data Index: 291747 (The Pile)

Max Activating Token Index: 143

Text #12

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1150783 (The Pile)

Max Activating Token Index: 690

Text #13

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.7230. Min Act: -0.0000

Data Index: 427218 (The Pile)

Max Activating Token Index: 478

Text #14

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.7354. Min Act: -0.0000

Data Index: 594032 (The Pile)

Max Activating Token Index: 426

Text #15

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.6857. Min Act: -0.0000

Data Index: 1560585 (The Pile)

Max Activating Token Index: 837

Text #16

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1537145 (The Pile)

Max Activating Token Index: 763

Text #17

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1318762 (The Pile)

Max Activating Token Index: 410

Text #18

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.6406. Min Act: -0.0000

Data Index: 166334 (The Pile)

Max Activating Token Index: 139

Text #19

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.6548. Min Act: -0.0000

Data Index: 934702 (The Pile)

Max Activating Token Index: 900