Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1921 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0156. Min Range: -2.0156

Max Act: 2.0156. Min Act: -0.0000

Data Index: 63013 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.9596. Min Act: -0.0000

Data Index: 1192519 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.8617. Min Act: -0.0000

Data Index: 153979 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.8284. Min Act: -0.0000

Data Index: 1369567 (Python Code)

Max Activating Token Index: 921

Text #4

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.7934. Min Act: -0.0000

Data Index: 1146106 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.6993. Min Act: -0.0000

Data Index: 1341336 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.6314. Min Act: -0.0000

Data Index: 112630 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.6260. Min Act: -0.0000

Data Index: 1323830 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.6215. Min Act: -0.0000

Data Index: 789987 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.7005. Min Act: -0.0000

Data Index: 279792 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.4764. Min Act: -0.0000

Data Index: 1039657 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.5145. Min Act: -0.0000

Data Index: 324879 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.5015. Min Act: -0.0000

Data Index: 306840 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.4918. Min Act: -0.0000

Data Index: 1043919 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.4880. Min Act: -0.0000

Data Index: 852605 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.4794. Min Act: -0.0000

Data Index: 1133033 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.3803. Min Act: -0.0000

Data Index: 410314 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.4579. Min Act: -0.0000

Data Index: 1073012 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.3737. Min Act: -0.0000

Data Index: 810555 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 2.0156. Min Range: -2.0156

Max Act: 1.4257. Min Act: -0.0000

Data Index: 1603625 (Python Code)

Max Activating Token Index: 67