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

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

Neuron 1321 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.1127. Min Act: -0.0000

Data Index: 23687 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.1047. Min Act: -0.0000

Data Index: 732245 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1355292 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1017874 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1277450 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0879. Min Act: -0.0000

Data Index: 31314 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0837. Min Act: -0.0000

Data Index: 301039 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0809. Min Act: -0.0000

Data Index: 254816 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0792. Min Act: -0.0000

Data Index: 673328 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1088640 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0771. Min Act: -0.0000

Data Index: 71613 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0745. Min Act: -0.0000

Data Index: 3167 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0817. Min Act: -0.0000

Data Index: 657769 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0754. Min Act: -0.0000

Data Index: 513069 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0750. Min Act: -0.0000

Data Index: 1242753 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0748. Min Act: -0.0000

Data Index: 332486 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0703. Min Act: -0.0000

Data Index: 71433 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0757. Min Act: -0.0000

Data Index: 264846 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0751. Min Act: -0.0000

Data Index: 1003489 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0608. Min Act: -0.0000

Data Index: 262657 (C4 (Web Text))

Max Activating Token Index: 256