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

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

Neuron 1589 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.8840. Min Act: -0.0000

Data Index: 212383 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1278284 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7501. Min Act: 0.0000

Data Index: 801247 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6772. Min Act: -0.0000

Data Index: 936148 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5649. Min Act: 0.0000

Data Index: 178779 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1166307 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5321. Min Act: -0.0000

Data Index: 145032 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5511. Min Act: -0.0000

Data Index: 493441 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5123. Min Act: -0.0000

Data Index: 239755 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5415. Min Act: -0.0000

Data Index: 107304 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5121. Min Act: -0.0000

Data Index: 973397 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5071. Min Act: -0.0000

Data Index: 867658 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5177. Min Act: -0.0000

Data Index: 909576 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1146530 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5291. Min Act: 0.0000

Data Index: 67150 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1183831 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5265. Min Act: 0.0000

Data Index: 1052559 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.4962. Min Act: 0.0000

Data Index: 705121 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5264. Min Act: -0.0000

Data Index: 1197160 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5184. Min Act: -0.0000

Data Index: 735059 (C4 (Web Text))

Max Activating Token Index: 711