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

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

Neuron 4200 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.7900. Min Act: -0.0002

Data Index: 929688 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.7352. Min Act: -0.0002

Data Index: 810234 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.7552. Min Act: -0.0002

Data Index: 1229708 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6672. Min Act: -0.0002

Data Index: 905312 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6876. Min Act: -0.0002

Data Index: 408149 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6657. Min Act: -0.0002

Data Index: 1031370 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6851. Min Act: -0.0002

Data Index: 1291036 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6547. Min Act: -0.0002

Data Index: 230378 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6791. Min Act: -0.0002

Data Index: 864613 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5516. Min Act: -0.0002

Data Index: 1220308 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6156. Min Act: -0.0002

Data Index: 12974 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.4645. Min Act: -0.0002

Data Index: 448625 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5814. Min Act: -0.0002

Data Index: 47236 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6873. Min Act: -0.0002

Data Index: 944329 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6145. Min Act: -0.0002

Data Index: 1257269 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6417. Min Act: -0.0002

Data Index: 410941 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6377. Min Act: -0.0002

Data Index: 264387 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5521. Min Act: -0.0002

Data Index: 773228 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6054. Min Act: -0.0002

Data Index: 92032 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5168. Min Act: -0.0002

Data Index: 887959 (C4 (Web Text))

Max Activating Token Index: 662