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

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

Neuron 446 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.3313. Min Act: -0.0001

Data Index: 87855 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2824. Min Act: -0.0001

Data Index: 584385 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2697. Min Act: -0.0001

Data Index: 969261 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2632. Min Act: -0.0001

Data Index: 940078 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2822. Min Act: -0.0001

Data Index: 409654 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2493. Min Act: -0.0001

Data Index: 1225503 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2649. Min Act: -0.0001

Data Index: 379770 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2578. Min Act: -0.0001

Data Index: 782969 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2616. Min Act: -0.0001

Data Index: 808009 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2481. Min Act: -0.0001

Data Index: 1045702 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2560. Min Act: -0.0001

Data Index: 66579 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2246. Min Act: -0.0001

Data Index: 717889 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2491. Min Act: -0.0001

Data Index: 359065 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2333. Min Act: -0.0001

Data Index: 644379 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2254. Min Act: -0.0001

Data Index: 507146 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2275. Min Act: -0.0001

Data Index: 1118815 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2228. Min Act: -0.0001

Data Index: 816485 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2418. Min Act: -0.0001

Data Index: 696194 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2212. Min Act: -0.0001

Data Index: 73329 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2314. Min Act: -0.0001

Data Index: 638011 (C4 (Web Text))

Max Activating Token Index: 582