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

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

Neuron 3722 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.1037. Min Act: -0.0001

Data Index: 252457 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1209443 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1231915 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0748. Min Act: -0.0000

Data Index: 337601 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0748. Min Act: -0.0001

Data Index: 788680 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0701. Min Act: -0.0000

Data Index: 1289478 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0698. Min Act: -0.0001

Data Index: 1355505 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0826. Min Act: -0.0001

Data Index: 1039737 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0711. Min Act: -0.0001

Data Index: 659556 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0726. Min Act: -0.0001

Data Index: 467342 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0698. Min Act: -0.0001

Data Index: 974143 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0717. Min Act: -0.0000

Data Index: 864680 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0690. Min Act: -0.0000

Data Index: 154823 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0704. Min Act: -0.0001

Data Index: 976559 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0714. Min Act: -0.0001

Data Index: 253993 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0736. Min Act: -0.0001

Data Index: 736050 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0702. Min Act: -0.0000

Data Index: 559530 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0726. Min Act: -0.0001

Data Index: 765654 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0696. Min Act: -0.0000

Data Index: 547125 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0716. Min Act: -0.0000

Data Index: 402927 (C4 (Web Text))

Max Activating Token Index: 260