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

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

Neuron 3538 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: 0.6715. Min Range: -0.6715

Max Act: 0.6715. Min Act: -0.0000

Data Index: 944147 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1122782 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.6088. Min Act: -0.0000

Data Index: 355674 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1277227 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.6169. Min Act: -0.0000

Data Index: 691803 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.5554. Min Act: -0.0000

Data Index: 403594 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1544058 (Python Code)

Max Activating Token Index: 706

Text #7

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.5748. Min Act: -0.0000

Data Index: 660612 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1133853 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.6311. Min Act: -0.0000

Data Index: 45801 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.5672. Min Act: -0.0000

Data Index: 852744 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.5655. Min Act: -0.0000

Data Index: 899631 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.5368. Min Act: -0.0000

Data Index: 177173 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.5170. Min Act: -0.0000

Data Index: 881848 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.5655. Min Act: -0.0000

Data Index: 1330759 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1205726 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.5899. Min Act: -0.0000

Data Index: 225510 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1181434 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.5495. Min Act: -0.0000

Data Index: 899022 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.6715. Min Range: -0.6715

Max Act: 0.4709. Min Act: -0.0000

Data Index: 320499 (C4 (Web Text))

Max Activating Token Index: 655