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

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

Neuron 2197 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.7042. Min Act: -0.0000

Data Index: 156915 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.6924. Min Act: -0.0000

Data Index: 557327 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.6789. Min Act: -0.0000

Data Index: 973729 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.4165. Min Act: -0.0000

Data Index: 478859 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.4203. Min Act: -0.0000

Data Index: 313467 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.4192. Min Act: -0.0000

Data Index: 219346 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.3760. Min Act: -0.0000

Data Index: 511611 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.3830. Min Act: -0.0000

Data Index: 918863 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1318361 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.3620. Min Act: -0.0000

Data Index: 975292 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.3464. Min Act: -0.0000

Data Index: 747423 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.3298. Min Act: -0.0000

Data Index: 63611 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.3245. Min Act: -0.0000

Data Index: 513740 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.3412. Min Act: -0.0000

Data Index: 1374553 (Python Code)

Max Activating Token Index: 914

Text #14

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.3394. Min Act: -0.0000

Data Index: 782405 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.3146. Min Act: -0.0000

Data Index: 445173 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.3249. Min Act: -0.0000

Data Index: 1325194 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1329297 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1090330 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.3183. Min Act: -0.0000

Data Index: 330263 (C4 (Web Text))

Max Activating Token Index: 298