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

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

Neuron 5199 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.2867. Min Range: -10.2867

Max Act: 10.2867. Min Act: -0.0000

Data Index: 881556 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 10.2867. Min Range: -10.2867

Max Act: 9.8157. Min Act: -0.0000

Data Index: 114233 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 10.2867. Min Range: -10.2867

Max Act: 9.9361. Min Act: -0.0000

Data Index: 714895 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 10.2867. Min Range: -10.2867

Max Act: 9.3639. Min Act: -0.0000

Data Index: 607025 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 10.2867. Min Range: -10.2867

Max Act: 9.6436. Min Act: -0.0000

Data Index: 650071 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 10.2867. Min Range: -10.2867

Max Act: 9.4404. Min Act: -0.0000

Data Index: 1019893 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 10.2867. Min Range: -10.2867

Max Act: 9.6293. Min Act: -0.0000

Data Index: 640757 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 10.2867. Min Range: -10.2867

Max Act: 9.3325. Min Act: -0.0000

Data Index: 1086615 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 10.2867. Min Range: -10.2867

Max Act: 9.1791. Min Act: -0.0000

Data Index: 657232 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 10.2867. Min Range: -10.2867

Max Act: 8.9030. Min Act: -0.0000

Data Index: 425596 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 10.2867. Min Range: -10.2867

Max Act: 9.0430. Min Act: -0.0000

Data Index: 855201 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 10.2867. Min Range: -10.2867

Max Act: 9.0251. Min Act: -0.0000

Data Index: 22889 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 10.2867. Min Range: -10.2867

Max Act: 8.8303. Min Act: -0.0000

Data Index: 1009180 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 10.2867. Min Range: -10.2867

Max Act: 8.7325. Min Act: -0.0000

Data Index: 787427 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 10.2867. Min Range: -10.2867

Max Act: 9.0246. Min Act: -0.0000

Data Index: 1076201 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 10.2867. Min Range: -10.2867

Max Act: 8.4198. Min Act: -0.0000

Data Index: 430219 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 10.2867. Min Range: -10.2867

Max Act: 8.4737. Min Act: -0.0000

Data Index: 972099 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 10.2867. Min Range: -10.2867

Max Act: 7.7357. Min Act: -0.0000

Data Index: 59894 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 10.2867. Min Range: -10.2867

Max Act: 7.3520. Min Act: -0.0000

Data Index: 995622 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 10.2867. Min Range: -10.2867

Max Act: 7.1581. Min Act: -0.0000

Data Index: 650818 (C4 (Web Text))

Max Activating Token Index: 743