Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3896 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1337. Min Act: -0.0002

Data Index: 1334284 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1349192 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1056. Min Act: -0.0002

Data Index: 418164 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0966. Min Act: -0.0002

Data Index: 69486 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1251993 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1298445 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0948. Min Act: -0.0002

Data Index: 346182 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0971. Min Act: -0.0001

Data Index: 603064 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0988. Min Act: -0.0002

Data Index: 847835 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0947. Min Act: -0.0002

Data Index: 293973 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0934. Min Act: -0.0002

Data Index: 698799 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0898. Min Act: -0.0002

Data Index: 92022 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0901. Min Act: -0.0002

Data Index: 470479 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0936. Min Act: -0.0001

Data Index: 855430 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0902. Min Act: -0.0002

Data Index: 419719 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0924. Min Act: -0.0002

Data Index: 684731 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0907. Min Act: -0.0002

Data Index: 696671 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1180414 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0864. Min Act: -0.0002

Data Index: 183034 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0922. Min Act: -0.0001

Data Index: 92899 (C4 (Web Text))

Max Activating Token Index: 428