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

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

Neuron 3090 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3768. Min Range: -5.3768

Max Act: 5.3768. Min Act: -0.0001

Data Index: 176999 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 5.3768. Min Range: -5.3768

Max Act: 5.2693. Min Act: -0.0001

Data Index: 602208 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 5.3768. Min Range: -5.3768

Max Act: 5.0583. Min Act: -0.0001

Data Index: 952860 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 5.3768. Min Range: -5.3768

Max Act: 5.0344. Min Act: -0.0001

Data Index: 622828 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 5.3768. Min Range: -5.3768

Max Act: 5.0327. Min Act: -0.0001

Data Index: 885157 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 5.3768. Min Range: -5.3768

Max Act: 5.0184. Min Act: -0.0001

Data Index: 1262037 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 5.3768. Min Range: -5.3768

Max Act: 5.1199. Min Act: -0.0001

Data Index: 201454 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 5.3768. Min Range: -5.3768

Max Act: 4.9075. Min Act: -0.0001

Data Index: 830094 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 5.3768. Min Range: -5.3768

Max Act: 4.8898. Min Act: -0.0001

Data Index: 744719 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 5.3768. Min Range: -5.3768

Max Act: 4.6260. Min Act: -0.0001

Data Index: 688813 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 5.3768. Min Range: -5.3768

Max Act: 4.7639. Min Act: -0.0001

Data Index: 1217854 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 5.3768. Min Range: -5.3768

Max Act: 4.7597. Min Act: -0.0001

Data Index: 661633 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 5.3768. Min Range: -5.3768

Max Act: 4.7577. Min Act: -0.0001

Data Index: 397314 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 5.3768. Min Range: -5.3768

Max Act: 4.6949. Min Act: -0.0001

Data Index: 179033 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 5.3768. Min Range: -5.3768

Max Act: 4.7065. Min Act: -0.0001

Data Index: 855226 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 5.3768. Min Range: -5.3768

Max Act: 4.7121. Min Act: -0.0001

Data Index: 461714 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 5.3768. Min Range: -5.3768

Max Act: 4.6314. Min Act: -0.0001

Data Index: 800353 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 5.3768. Min Range: -5.3768

Max Act: 4.6206. Min Act: -0.0001

Data Index: 909785 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 5.3768. Min Range: -5.3768

Max Act: 4.6244. Min Act: -0.0001

Data Index: 369749 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 5.3768. Min Range: -5.3768

Max Act: 4.5878. Min Act: -0.0001

Data Index: 285797 (C4 (Web Text))

Max Activating Token Index: 84