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

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

Neuron 3306 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: 0.6954. Min Range: -0.6954

Max Act: 0.6954. Min Act: -0.0000

Data Index: 826593 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6364. Min Act: 0.0000

Data Index: 1042235 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1113405 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1145281 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1355500 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5271. Min Act: 0.0000

Data Index: 373212 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5896. Min Act: -0.0000

Data Index: 992961 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5701. Min Act: -0.0000

Data Index: 666364 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5364. Min Act: -0.0000

Data Index: 690594 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5397. Min Act: -0.0000

Data Index: 359663 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.4963. Min Act: 0.0000

Data Index: 492039 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.4611. Min Act: -0.0000

Data Index: 13644 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5113. Min Act: 0.0000

Data Index: 170180 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1334709 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.4790. Min Act: -0.0000

Data Index: 408528 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5064. Min Act: -0.0000

Data Index: 580329 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.4611. Min Act: -0.0000

Data Index: 1595839 (Python Code)

Max Activating Token Index: 808

Text #17

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.4602. Min Act: -0.0000

Data Index: 550132 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.4744. Min Act: -0.0000

Data Index: 213805 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.4255. Min Act: -0.0000

Data Index: 999934 (C4 (Web Text))

Max Activating Token Index: 742