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

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

Neuron 4140 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0764. Min Range: -1.0764

Max Act: 1.0764. Min Act: -0.0000

Data Index: 542410 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1208581 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1014899 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8991. Min Act: -0.0000

Data Index: 1129793 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8481. Min Act: -0.0000

Data Index: 576268 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8255. Min Act: -0.0000

Data Index: 667140 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8736. Min Act: -0.0000

Data Index: 343347 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1111716 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8086. Min Act: -0.0000

Data Index: 501114 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7729. Min Act: -0.0000

Data Index: 784658 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7452. Min Act: -0.0000

Data Index: 258371 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7660. Min Act: -0.0000

Data Index: 112793 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1024714 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7309. Min Act: -0.0000

Data Index: 972876 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7219. Min Act: -0.0000

Data Index: 394540 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7692. Min Act: -0.0000

Data Index: 460003 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7632. Min Act: -0.0000

Data Index: 647054 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7440. Min Act: -0.0000

Data Index: 320640 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7841. Min Act: -0.0000

Data Index: 905797 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7533. Min Act: -0.0000

Data Index: 985526 (C4 (Web Text))

Max Activating Token Index: 445