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

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

Neuron 3639 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8915. Min Act: -0.0000

Data Index: 299154 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8617. Min Act: -0.0000

Data Index: 138157 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7907. Min Act: -0.0000

Data Index: 27880 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1335215 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1170581 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1151989 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7130. Min Act: -0.0000

Data Index: 349699 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1027955 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1031253 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.7013. Min Act: -0.0000

Data Index: 7550 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6424. Min Act: -0.0000

Data Index: 208021 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6326. Min Act: -0.0000

Data Index: 444690 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1014121 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1147330 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.5930. Min Act: -0.0000

Data Index: 335929 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.5867. Min Act: -0.0000

Data Index: 993634 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6060. Min Act: -0.0000

Data Index: 360871 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1074456 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6698. Min Act: -0.0000

Data Index: 713850 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.8915. Min Range: -0.8915

Max Act: 0.6165. Min Act: -0.0000

Data Index: 891544 (C4 (Web Text))

Max Activating Token Index: 864