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

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

Neuron 355 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: 1.1610. Min Range: -1.1610

Max Act: 1.1610. Min Act: -0.0000

Data Index: 1102871 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 1.1610. Min Range: -1.1610

Max Act: 1.1046. Min Act: -0.0000

Data Index: 595132 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 1.1610. Min Range: -1.1610

Max Act: 1.1022. Min Act: -0.0000

Data Index: 467621 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 1.1610. Min Range: -1.1610

Max Act: 1.0858. Min Act: -0.0000

Data Index: 1474148 (Python Code)

Max Activating Token Index: 735

Text #4

Max Range: 1.1610. Min Range: -1.1610

Max Act: 1.0368. Min Act: -0.0000

Data Index: 1622012 (Python Code)

Max Activating Token Index: 87

Text #5

Max Range: 1.1610. Min Range: -1.1610

Max Act: 1.0125. Min Act: -0.0001

Data Index: 1364804 (Python Code)

Max Activating Token Index: 288

Text #6

Max Range: 1.1610. Min Range: -1.1610

Max Act: 1.0371. Min Act: -0.0000

Data Index: 810160 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 1.1610. Min Range: -1.1610

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1525341 (Python Code)

Max Activating Token Index: 496

Text #8

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9848. Min Act: -0.0000

Data Index: 1425737 (Python Code)

Max Activating Token Index: 696

Text #9

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1623956 (Python Code)

Max Activating Token Index: 770

Text #10

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9513. Min Act: -0.0000

Data Index: 528113 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9414. Min Act: -0.0000

Data Index: 1536440 (Python Code)

Max Activating Token Index: 691

Text #12

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1462863 (Python Code)

Max Activating Token Index: 65

Text #13

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9536. Min Act: -0.0000

Data Index: 138169 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1618732 (Python Code)

Max Activating Token Index: 890

Text #15

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8590. Min Act: -0.0000

Data Index: 305800 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9095. Min Act: -0.0000

Data Index: 883876 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1141857 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8667. Min Act: -0.0000

Data Index: 803384 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1568117 (Python Code)

Max Activating Token Index: 307