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

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

Neuron 3193 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1606. Min Act: -0.0001

Data Index: 189583 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1651. Min Act: -0.0001

Data Index: 1282595 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1300. Min Act: -0.0001

Data Index: 214686 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1241. Min Act: -0.0001

Data Index: 178991 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1009709 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1075. Min Act: -0.0001

Data Index: 302715 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1228974 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1001. Min Act: -0.0001

Data Index: 929462 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1280278 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1150. Min Act: -0.0001

Data Index: 27491 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1040. Min Act: -0.0001

Data Index: 33945 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1200176 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1169. Min Act: -0.0001

Data Index: 1228773 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1014. Min Act: -0.0001

Data Index: 400128 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.0890. Min Act: -0.0001

Data Index: 629415 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.0886. Min Act: -0.0001

Data Index: 422394 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.0992. Min Act: -0.0001

Data Index: 841788 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.0954. Min Act: -0.0001

Data Index: 275669 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.0883. Min Act: -0.0001

Data Index: 715168 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1240030 (C4 (Web Text))

Max Activating Token Index: 980