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

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

Neuron 524 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2544. Min Range: -1.2544

Max Act: 1.2544. Min Act: -0.0000

Data Index: 1012617 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.9482. Min Act: 0.0000

Data Index: 1058652 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.8994. Min Act: -0.0000

Data Index: 1291948 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.8101. Min Act: -0.0000

Data Index: 278974 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.7204. Min Act: -0.0000

Data Index: 388329 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.7568. Min Act: -0.0000

Data Index: 420530 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.7779. Min Act: 0.0002

Data Index: 848481 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1057256 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.7168. Min Act: -0.0000

Data Index: 1062497 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.6699. Min Act: 0.0002

Data Index: 821160 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.6750. Min Act: -0.0000

Data Index: 200362 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.6728. Min Act: -0.0000

Data Index: 547359 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.6712. Min Act: -0.0000

Data Index: 822633 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1316318 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.6347. Min Act: 0.0000

Data Index: 916773 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.6524. Min Act: -0.0000

Data Index: 959944 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1134431 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1280192 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.6421. Min Act: 0.0002

Data Index: 937696 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 1.2544. Min Range: -1.2544

Max Act: 0.6600. Min Act: -0.0000

Data Index: 319004 (C4 (Web Text))

Max Activating Token Index: 818