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

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

Neuron 1080 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: 0.0980. Min Range: -0.0980

Max Act: 0.0980. Min Act: -0.0001

Data Index: 1079456 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0915. Min Act: -0.0002

Data Index: 29201 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1193408 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1193594 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0736. Min Act: -0.0001

Data Index: 895837 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1192439 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0432. Min Act: -0.0001

Data Index: 37182 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1103138 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0304. Min Act: -0.0001

Data Index: 789146 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0266. Min Act: -0.0001

Data Index: 1277953 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0271. Min Act: -0.0001

Data Index: 91919 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0267. Min Act: -0.0001

Data Index: 978481 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0262. Min Act: -0.0001

Data Index: 104320 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0262. Min Act: -0.0001

Data Index: 212448 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0254. Min Act: -0.0001

Data Index: 278916 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1371889 (Python Code)

Max Activating Token Index: 845

Text #16

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0234. Min Act: -0.0001

Data Index: 1183374 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0242. Min Act: -0.0001

Data Index: 444217 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0248. Min Act: -0.0001

Data Index: 765283 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0237. Min Act: -0.0001

Data Index: 705294 (C4 (Web Text))

Max Activating Token Index: 32