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

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

Neuron 2715 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: 1.2289. Min Range: -1.2289

Max Act: 1.2289. Min Act: -0.0002

Data Index: 1320672 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 1.2289. Min Range: -1.2289

Max Act: 1.0541. Min Act: -0.0001

Data Index: 1342464 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.9415. Min Act: -0.0002

Data Index: 14917 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.9625. Min Act: -0.0002

Data Index: 1134334 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.9882. Min Act: -0.0001

Data Index: 1046472 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.9007. Min Act: -0.0002

Data Index: 513995 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.8679. Min Act: -0.0002

Data Index: 1237278 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.9017. Min Act: -0.0001

Data Index: 681963 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.7285. Min Act: -0.0002

Data Index: 1142131 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.8691. Min Act: -0.0002

Data Index: 91708 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.7841. Min Act: -0.0002

Data Index: 182151 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.8502. Min Act: -0.0001

Data Index: 18450 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.8384. Min Act: -0.0001

Data Index: 1038544 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.8412. Min Act: -0.0002

Data Index: 751145 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.8342. Min Act: -0.0001

Data Index: 573252 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.8065. Min Act: -0.0002

Data Index: 697701 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.8243. Min Act: -0.0001

Data Index: 326830 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.8330. Min Act: -0.0002

Data Index: 205982 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.7283. Min Act: -0.0002

Data Index: 389250 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 1.2289. Min Range: -1.2289

Max Act: 0.8412. Min Act: -0.0002

Data Index: 109569 (C4 (Web Text))

Max Activating Token Index: 263