Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3902 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0553. Min Range: -2.0553

Max Act: 2.0553. Min Act: -0.0000

Data Index: 1145089 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.9885. Min Act: -0.0000

Data Index: 296519 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.8487. Min Act: -0.0000

Data Index: 1080584 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.6985. Min Act: -0.0000

Data Index: 865780 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.7503. Min Act: -0.0000

Data Index: 230247 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.7493. Min Act: -0.0000

Data Index: 509219 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.8060. Min Act: -0.0000

Data Index: 865286 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.7758. Min Act: -0.0000

Data Index: 1166298 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.7618. Min Act: -0.0000

Data Index: 1144007 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.7495. Min Act: -0.0000

Data Index: 967980 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.7044. Min Act: -0.0000

Data Index: 7101 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.6765. Min Act: -0.0000

Data Index: 140622 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.7239. Min Act: -0.0000

Data Index: 1150687 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.7206. Min Act: -0.0000

Data Index: 251644 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.7158. Min Act: -0.0000

Data Index: 895615 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.6088. Min Act: -0.0000

Data Index: 786661 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.6841. Min Act: -0.0000

Data Index: 748373 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.6886. Min Act: -0.0000

Data Index: 881370 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.6411. Min Act: -0.0000

Data Index: 479400 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 2.0553. Min Range: -2.0553

Max Act: 1.6317. Min Act: -0.0000

Data Index: 311019 (C4 (Web Text))

Max Activating Token Index: 25