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

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

Neuron 534 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0539. Min Range: -2.0539

Max Act: 2.0539. Min Act: -0.0000

Data Index: 330314 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.8552. Min Act: -0.0000

Data Index: 1300290 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.8260. Min Act: -0.0000

Data Index: 1211587 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.6642. Min Act: -0.0000

Data Index: 1212813 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.7516. Min Act: -0.0000

Data Index: 360058 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.6009. Min Act: -0.0000

Data Index: 593742 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.5142. Min Act: -0.0000

Data Index: 393254 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.6038. Min Act: -0.0000

Data Index: 73816 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.4722. Min Act: -0.0000

Data Index: 418712 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.5306. Min Act: -0.0000

Data Index: 442257 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.4982. Min Act: -0.0001

Data Index: 835190 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.5098. Min Act: -0.0000

Data Index: 1053760 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.4647. Min Act: -0.0000

Data Index: 959922 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.4564. Min Act: -0.0000

Data Index: 964557 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.4090. Min Act: -0.0001

Data Index: 841357 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.4954. Min Act: -0.0000

Data Index: 475223 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.4938. Min Act: -0.0000

Data Index: 406019 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.4214. Min Act: -0.0000

Data Index: 561821 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.4191. Min Act: -0.0000

Data Index: 27463 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 2.0539. Min Range: -2.0539

Max Act: 1.4488. Min Act: -0.0000

Data Index: 906654 (C4 (Web Text))

Max Activating Token Index: 105