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

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

Neuron 507 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.8111. Min Act: -0.0000

Data Index: 236698 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.8338. Min Act: 0.0001

Data Index: 644556 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1277825 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.6907. Min Act: -0.0000

Data Index: 751723 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7087. Min Act: -0.0000

Data Index: 895765 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.6311. Min Act: 0.0001

Data Index: 698124 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1299844 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1013267 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.5800. Min Act: 0.0000

Data Index: 1134027 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.5567. Min Act: -0.0000

Data Index: 370229 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.5302. Min Act: 0.0000

Data Index: 1162326 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.5588. Min Act: -0.0000

Data Index: 844568 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.5835. Min Act: -0.0000

Data Index: 886288 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.5014. Min Act: -0.0000

Data Index: 987376 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.5336. Min Act: -0.0000

Data Index: 551237 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.5058. Min Act: -0.0000

Data Index: 674615 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.4997. Min Act: -0.0000

Data Index: 811755 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1262341 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.5064. Min Act: -0.0000

Data Index: 909880 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.4964. Min Act: -0.0000

Data Index: 306250 (C4 (Web Text))

Max Activating Token Index: 673