Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 736 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1173512 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.6398. Min Act: -0.0000

Data Index: 977185 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5824. Min Act: -0.0000

Data Index: 289451 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5914. Min Act: -0.0000

Data Index: 41949 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5874. Min Act: -0.0000

Data Index: 459945 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5727. Min Act: -0.0000

Data Index: 351930 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5495. Min Act: -0.0000

Data Index: 777962 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5638. Min Act: -0.0000

Data Index: 304342 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5271. Min Act: -0.0000

Data Index: 380544 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5472. Min Act: -0.0000

Data Index: 791233 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5400. Min Act: -0.0000

Data Index: 63666 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5414. Min Act: -0.0000

Data Index: 28609 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5242. Min Act: -0.0000

Data Index: 579374 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5012. Min Act: -0.0000

Data Index: 59706 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5452. Min Act: -0.0000

Data Index: 969121 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5253. Min Act: -0.0000

Data Index: 474195 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5271. Min Act: -0.0000

Data Index: 874132 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1228627 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5250. Min Act: -0.0000

Data Index: 704524 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.6398. Min Range: -0.6398

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1272623 (C4 (Web Text))

Max Activating Token Index: 654