Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 23 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0916. Min Range: -2.0916

Max Act: 2.0916. Min Act: -0.0000

Data Index: 1249434 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.5476. Min Act: -0.0000

Data Index: 316164 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.5955. Min Act: -0.0000

Data Index: 406468 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.5231. Min Act: -0.0000

Data Index: 129327 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.3468. Min Act: -0.0000

Data Index: 284288 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.5457. Min Act: -0.0000

Data Index: 603544 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.2787. Min Act: -0.0000

Data Index: 81155 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.3073. Min Act: -0.0000

Data Index: 882363 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.3352. Min Act: -0.0000

Data Index: 1309184 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.3896. Min Act: -0.0000

Data Index: 203302 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.1752. Min Act: -0.0000

Data Index: 546534 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.1357. Min Act: -0.0000

Data Index: 511202 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.4840. Min Act: -0.0000

Data Index: 687321 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.2379. Min Act: -0.0000

Data Index: 103423 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.2561. Min Act: -0.0000

Data Index: 975210 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.2127. Min Act: -0.0000

Data Index: 546904 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.1514. Min Act: -0.0000

Data Index: 664599 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.2912. Min Act: -0.0000

Data Index: 441457 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.1873. Min Act: -0.0000

Data Index: 549552 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 2.0916. Min Range: -2.0916

Max Act: 1.2720. Min Act: -0.0000

Data Index: 293879 (C4 (Web Text))

Max Activating Token Index: 457