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

Dataset: The Pile

Neuron 901 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: 0.1367. Min Range: -0.1367

Max Act: 0.1197. Min Act: -0.0000

Data Index: 895688 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1102. Min Act: -0.0000

Data Index: 514605 (The Pile)

Max Activating Token Index: 1015

Text #2

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1478018 (The Pile)

Max Activating Token Index: 123

Text #3

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1367. Min Act: -0.0000

Data Index: 1056186 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1016. Min Act: -0.0000

Data Index: 1796584 (The Pile)

Max Activating Token Index: 309

Text #5

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0842. Min Act: -0.0000

Data Index: 253387 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0914. Min Act: -0.0000

Data Index: 205504 (The Pile)

Max Activating Token Index: 1016

Text #7

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0903. Min Act: -0.0000

Data Index: 513653 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1271068 (The Pile)

Max Activating Token Index: 147

Text #9

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0873. Min Act: -0.0000

Data Index: 575346 (The Pile)

Max Activating Token Index: 447

Text #10

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1664873 (The Pile)

Max Activating Token Index: 967

Text #11

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0830. Min Act: -0.0000

Data Index: 709295 (The Pile)

Max Activating Token Index: 435

Text #12

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0790. Min Act: -0.0000

Data Index: 1359895 (The Pile)

Max Activating Token Index: 50

Text #13

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0790. Min Act: -0.0000

Data Index: 322346 (The Pile)

Max Activating Token Index: 421

Text #14

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0721. Min Act: -0.0000

Data Index: 194210 (The Pile)

Max Activating Token Index: 217

Text #15

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1997311 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0743. Min Act: -0.0000

Data Index: 1298560 (The Pile)

Max Activating Token Index: 663

Text #17

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0681. Min Act: -0.0000

Data Index: 1472426 (The Pile)

Max Activating Token Index: 366

Text #18

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1598510 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1989034 (The Pile)

Max Activating Token Index: 575