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

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

Neuron 3633 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.7193. Min Act: -0.0000

Data Index: 1171840 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.8996. Min Act: -0.0000

Data Index: 79982 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.7575. Min Act: -0.0000

Data Index: 253880 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.6106. Min Act: -0.0001

Data Index: 697897 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.6918. Min Act: -0.0000

Data Index: 359934 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.5573. Min Act: -0.0000

Data Index: 657886 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.7073. Min Act: -0.0000

Data Index: 592616 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.3269. Min Act: -0.0000

Data Index: 1354893 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.5823. Min Act: -0.0000

Data Index: 817481 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.4923. Min Act: -0.0000

Data Index: 168095 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.5149. Min Act: -0.0000

Data Index: 259093 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.6350. Min Act: -0.0000

Data Index: 1016463 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.5370. Min Act: -0.0000

Data Index: 1353768 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.4981. Min Act: -0.0000

Data Index: 1038497 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.4068. Min Act: -0.0000

Data Index: 343343 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.5180. Min Act: -0.0000

Data Index: 864314 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.6179. Min Act: -0.0000

Data Index: 728251 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.2050. Min Act: -0.0001

Data Index: 1085184 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.2271. Min Act: -0.0000

Data Index: 679633 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 1.8996. Min Range: -1.8996

Max Act: 1.4402. Min Act: -0.0000

Data Index: 28841 (C4 (Web Text))

Max Activating Token Index: 244