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

Dataset: The Pile

Neuron 3501 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1079600 (The Pile)

Max Activating Token Index: 892

Text #1

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1245443 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4620. Min Act: -0.0000

Data Index: 64586 (The Pile)

Max Activating Token Index: 480

Text #3

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4858. Min Act: -0.0000

Data Index: 675291 (The Pile)

Max Activating Token Index: 598

Text #4

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4155. Min Act: -0.0000

Data Index: 338143 (The Pile)

Max Activating Token Index: 922

Text #5

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1776290 (The Pile)

Max Activating Token Index: 346

Text #6

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1502885 (The Pile)

Max Activating Token Index: 769

Text #7

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1715009 (The Pile)

Max Activating Token Index: 812

Text #8

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4851. Min Act: -0.0000

Data Index: 174975 (The Pile)

Max Activating Token Index: 664

Text #9

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1670075 (The Pile)

Max Activating Token Index: 378

Text #10

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4448. Min Act: -0.0000

Data Index: 468468 (The Pile)

Max Activating Token Index: 740

Text #11

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4127. Min Act: -0.0000

Data Index: 939385 (The Pile)

Max Activating Token Index: 690

Text #12

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4159. Min Act: -0.0000

Data Index: 168860 (The Pile)

Max Activating Token Index: 745

Text #13

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1627476 (The Pile)

Max Activating Token Index: 920

Text #14

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3962. Min Act: -0.0000

Data Index: 1054041 (The Pile)

Max Activating Token Index: 326

Text #15

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1057949 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1457173 (The Pile)

Max Activating Token Index: 426

Text #17

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4048. Min Act: -0.0000

Data Index: 42404 (The Pile)

Max Activating Token Index: 927

Text #18

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1950191 (The Pile)

Max Activating Token Index: 474

Text #19

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4050. Min Act: -0.0000

Data Index: 816990 (The Pile)

Max Activating Token Index: 677