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

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

Neuron 4596 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.9003. Min Act: -0.0000

Data Index: 405379 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1254181 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.8332. Min Act: -0.0000

Data Index: 845988 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.8063. Min Act: -0.0000

Data Index: 497436 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1162100 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7791. Min Act: -0.0000

Data Index: 733005 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7768. Min Act: -0.0000

Data Index: 397163 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7781. Min Act: -0.0000

Data Index: 428435 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7928. Min Act: -0.0000

Data Index: 57177 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1030964 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7563. Min Act: -0.0000

Data Index: 636741 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7842. Min Act: -0.0000

Data Index: 190756 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7813. Min Act: -0.0000

Data Index: 970420 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7301. Min Act: -0.0000

Data Index: 995455 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1051640 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7670. Min Act: -0.0000

Data Index: 387414 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7233. Min Act: -0.0000

Data Index: 944816 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7338. Min Act: -0.0000

Data Index: 143797 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7294. Min Act: -0.0000

Data Index: 629085 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7673. Min Act: -0.0000

Data Index: 194009 (C4 (Web Text))

Max Activating Token Index: 159