Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1752 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2694. Min Act: -0.0002

Data Index: 1269521 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2433. Min Act: -0.0003

Data Index: 482998 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2328. Min Act: -0.0003

Data Index: 365991 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2374. Min Act: -0.0003

Data Index: 742926 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2207. Min Act: -0.0003

Data Index: 7181 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2282. Min Act: -0.0003

Data Index: 376237 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2190. Min Act: -0.0003

Data Index: 154204 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2239. Min Act: -0.0003

Data Index: 488995 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2054. Min Act: -0.0003

Data Index: 950546 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2185. Min Act: -0.0003

Data Index: 73076 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1996. Min Act: -0.0004

Data Index: 122478 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2062. Min Act: -0.0003

Data Index: 288491 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1990. Min Act: -0.0003

Data Index: 468398 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2026. Min Act: -0.0003

Data Index: 1194695 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1925. Min Act: -0.0003

Data Index: 500264 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1982. Min Act: -0.0003

Data Index: 677870 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1990. Min Act: -0.0003

Data Index: 798743 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2023. Min Act: -0.0004

Data Index: 1113365 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1994. Min Act: -0.0003

Data Index: 1138913 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1911. Min Act: -0.0003

Data Index: 1141698 (C4 (Web Text))

Max Activating Token Index: 643