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

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

Neuron 3454 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2418. Min Range: -1.2418

Max Act: 1.2418. Min Act: -0.0000

Data Index: 949298 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 1.2418. Min Range: -1.2418

Max Act: 1.1008. Min Act: -0.0000

Data Index: 1209933 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 1.2418. Min Range: -1.2418

Max Act: 1.0895. Min Act: -0.0000

Data Index: 406874 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.9645. Min Act: -0.0000

Data Index: 131730 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.9820. Min Act: -0.0000

Data Index: 19260 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1006633 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.9211. Min Act: -0.0000

Data Index: 1330921 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.8899. Min Act: -0.0000

Data Index: 339779 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.8305. Min Act: -0.0000

Data Index: 348751 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.7717. Min Act: -0.0000

Data Index: 788783 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.8451. Min Act: -0.0000

Data Index: 181477 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.8146. Min Act: -0.0000

Data Index: 686652 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.7792. Min Act: -0.0000

Data Index: 924669 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.8080. Min Act: -0.0000

Data Index: 970708 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.8049. Min Act: -0.0000

Data Index: 829889 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.7680. Min Act: -0.0000

Data Index: 991320 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.7916. Min Act: -0.0000

Data Index: 39926 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.7233. Min Act: -0.0000

Data Index: 38657 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1180818 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 1.2418. Min Range: -1.2418

Max Act: 0.7403. Min Act: -0.0000

Data Index: 221024 (C4 (Web Text))

Max Activating Token Index: 858