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

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

Neuron 4224 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7549. Min Range: -1.7549

Max Act: 1.7549. Min Act: -0.0000

Data Index: 1167206 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 1.7549. Min Range: -1.7549

Max Act: 1.5365. Min Act: -0.0000

Data Index: 109827 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 1.7549. Min Range: -1.7549

Max Act: 1.4697. Min Act: -0.0000

Data Index: 1188558 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 1.7549. Min Range: -1.7549

Max Act: 1.3983. Min Act: -0.0000

Data Index: 341401 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 1.7549. Min Range: -1.7549

Max Act: 1.4184. Min Act: -0.0000

Data Index: 1272783 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 1.7549. Min Range: -1.7549

Max Act: 1.4221. Min Act: -0.0000

Data Index: 1263935 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.7549. Min Range: -1.7549

Max Act: 1.3659. Min Act: -0.0000

Data Index: 109253 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 1.7549. Min Range: -1.7549

Max Act: 1.3311. Min Act: -0.0000

Data Index: 271307 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 1.7549. Min Range: -1.7549

Max Act: 1.2273. Min Act: 0.0000

Data Index: 554221 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 1.7549. Min Range: -1.7549

Max Act: 1.2268. Min Act: -0.0000

Data Index: 578872 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 1.7549. Min Range: -1.7549

Max Act: 1.1496. Min Act: -0.0000

Data Index: 252809 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.7549. Min Range: -1.7549

Max Act: 0.9666. Min Act: -0.0000

Data Index: 160859 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 1.7549. Min Range: -1.7549

Max Act: 0.9307. Min Act: -0.0000

Data Index: 1228629 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 1.7549. Min Range: -1.7549

Max Act: 0.8452. Min Act: -0.0000

Data Index: 746980 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 1.7549. Min Range: -1.7549

Max Act: 0.7884. Min Act: -0.0000

Data Index: 1257243 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 1.7549. Min Range: -1.7549

Max Act: 0.8379. Min Act: -0.0000

Data Index: 599356 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 1.7549. Min Range: -1.7549

Max Act: 0.7521. Min Act: -0.0000

Data Index: 280143 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.7549. Min Range: -1.7549

Max Act: 0.7784. Min Act: -0.0000

Data Index: 808533 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 1.7549. Min Range: -1.7549

Max Act: 0.7840. Min Act: -0.0000

Data Index: 914000 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 1.7549. Min Range: -1.7549

Max Act: 0.7312. Min Act: -0.0000

Data Index: 39926 (C4 (Web Text))

Max Activating Token Index: 798