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

Dataset: The Pile

Neuron 4095 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: 0.8219. Min Range: -0.8219

Max Act: 0.7422. Min Act: -0.0000

Data Index: 810448 (The Pile)

Max Activating Token Index: 236

Text #1

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1325228 (The Pile)

Max Activating Token Index: 598

Text #2

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6312. Min Act: -0.0000

Data Index: 887365 (The Pile)

Max Activating Token Index: 101

Text #3

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6390. Min Act: -0.0000

Data Index: 920508 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6977. Min Act: -0.0000

Data Index: 1795351 (The Pile)

Max Activating Token Index: 933

Text #5

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6949. Min Act: -0.0000

Data Index: 1396577 (The Pile)

Max Activating Token Index: 869

Text #6

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1148114 (The Pile)

Max Activating Token Index: 1011

Text #7

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6204. Min Act: -0.0000

Data Index: 403936 (The Pile)

Max Activating Token Index: 508

Text #8

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1359874 (The Pile)

Max Activating Token Index: 154

Text #9

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5532. Min Act: -0.0000

Data Index: 843365 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1557646 (The Pile)

Max Activating Token Index: 166

Text #11

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1471812 (The Pile)

Max Activating Token Index: 638

Text #12

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1621527 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5550. Min Act: -0.0000

Data Index: 782411 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1622242 (The Pile)

Max Activating Token Index: 567

Text #15

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1025121 (The Pile)

Max Activating Token Index: 624

Text #16

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1625937 (The Pile)

Max Activating Token Index: 395

Text #17

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1384084 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1373224 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5326. Min Act: -0.0000

Data Index: 877522 (The Pile)

Max Activating Token Index: 717