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

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

Neuron 3036 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.5486. Min Act: -0.0000

Data Index: 868268 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.5281. Min Act: -0.0000

Data Index: 768546 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4028. Min Act: -0.0000

Data Index: 985592 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.3920. Min Act: -0.0000

Data Index: 906523 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.3859. Min Act: -0.0000

Data Index: 872884 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.3716. Min Act: -0.0000

Data Index: 580857 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1323736 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.3324. Min Act: -0.0000

Data Index: 663828 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.3404. Min Act: -0.0000

Data Index: 464567 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1010173 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.3271. Min Act: -0.0000

Data Index: 1238828 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.2941. Min Act: -0.0000

Data Index: 124498 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.3033. Min Act: -0.0000

Data Index: 203291 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.3015. Min Act: -0.0000

Data Index: 551853 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.3067. Min Act: -0.0000

Data Index: 979775 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.2869. Min Act: -0.0000

Data Index: 767666 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.2851. Min Act: -0.0000

Data Index: 849272 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.2832. Min Act: -0.0000

Data Index: 220365 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1246772 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1063729 (C4 (Web Text))

Max Activating Token Index: 749