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

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

Neuron 2016 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1165083 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.7583. Min Act: -0.0000

Data Index: 618477 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1115657 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6438. Min Act: -0.0000

Data Index: 657500 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5995. Min Act: -0.0000

Data Index: 7012 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5957. Min Act: -0.0000

Data Index: 364467 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5880. Min Act: -0.0000

Data Index: 465419 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1185354 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5902. Min Act: -0.0000

Data Index: 803672 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5916. Min Act: -0.0000

Data Index: 446989 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5793. Min Act: -0.0000

Data Index: 319687 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1054911 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5541. Min Act: -0.0000

Data Index: 508418 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5705. Min Act: -0.0000

Data Index: 816598 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5884. Min Act: -0.0000

Data Index: 687457 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5648. Min Act: -0.0000

Data Index: 885754 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5410. Min Act: -0.0000

Data Index: 555696 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5527. Min Act: -0.0000

Data Index: 211357 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5333. Min Act: -0.0000

Data Index: 160804 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1239854 (C4 (Web Text))

Max Activating Token Index: 802