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

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

Neuron 5423 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: 4.1254. Min Range: -4.1254

Max Act: 4.1254. Min Act: -0.0000

Data Index: 29201 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.4798. Min Act: -0.0000

Data Index: 1079456 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.9501. Min Act: -0.0000

Data Index: 1425695 (Python Code)

Max Activating Token Index: 1012

Text #3

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.9477. Min Act: -0.0000

Data Index: 1508041 (Python Code)

Max Activating Token Index: 928

Text #4

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.6661. Min Act: -0.0000

Data Index: 1380316 (Python Code)

Max Activating Token Index: 878

Text #5

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.3133. Min Act: -0.0000

Data Index: 547867 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.4709. Min Act: -0.0000

Data Index: 1244522 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.2144. Min Act: -0.0000

Data Index: 928723 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.2921. Min Act: -0.0000

Data Index: 1376897 (Python Code)

Max Activating Token Index: 766

Text #9

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.4073. Min Act: -0.0000

Data Index: 1053730 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.3759. Min Act: -0.0000

Data Index: 597744 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 4.1254. Min Range: -4.1254

Max Act: 1.9823. Min Act: -0.0000

Data Index: 208527 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.1894. Min Act: -0.0000

Data Index: 820023 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.0565. Min Act: -0.0000

Data Index: 177017 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.1697. Min Act: -0.0000

Data Index: 1580424 (Python Code)

Max Activating Token Index: 760

Text #15

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.1572. Min Act: -0.0000

Data Index: 1000208 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.1248. Min Act: -0.0000

Data Index: 318926 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.0950. Min Act: -0.0000

Data Index: 544886 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 4.1254. Min Range: -4.1254

Max Act: 1.9537. Min Act: -0.0000

Data Index: 965543 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 4.1254. Min Range: -4.1254

Max Act: 2.0605. Min Act: -0.0000

Data Index: 1117632 (C4 (Web Text))

Max Activating Token Index: 452