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

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

Neuron 4664 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: 0.5053. Min Range: -0.5053

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1082557 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1024702 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.4160. Min Act: -0.0000

Data Index: 355749 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1071694 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1039003 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1193291 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1066207 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3436. Min Act: -0.0000

Data Index: 440485 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3117. Min Act: -0.0000

Data Index: 40452 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1288673 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3267. Min Act: -0.0000

Data Index: 296464 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3062. Min Act: -0.0000

Data Index: 873720 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3658. Min Act: -0.0000

Data Index: 852997 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3902. Min Act: -0.0000

Data Index: 61918 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1069307 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3298. Min Act: -0.0000

Data Index: 623908 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2629. Min Act: -0.0000

Data Index: 928167 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2911. Min Act: -0.0000

Data Index: 863167 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2779. Min Act: -0.0000

Data Index: 677934 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2571. Min Act: -0.0000

Data Index: 110471 (C4 (Web Text))

Max Activating Token Index: 281