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

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

Neuron 3563 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.1194. Min Act: -0.0000

Data Index: 321036 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.9243. Min Act: -0.0000

Data Index: 275125 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0029. Min Act: -0.0000

Data Index: 557658 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.0687. Min Act: -0.0000

Data Index: 783299 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.9267. Min Act: -0.0000

Data Index: 976916 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.9072. Min Act: -0.0000

Data Index: 1410883 (Python Code)

Max Activating Token Index: 949

Text #6

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.8697. Min Act: -0.0000

Data Index: 819996 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.9724. Min Act: -0.0000

Data Index: 814450 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1506136 (Python Code)

Max Activating Token Index: 878

Text #9

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.8604. Min Act: -0.0000

Data Index: 1377580 (Python Code)

Max Activating Token Index: 972

Text #10

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1205826 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1645153 (Python Code)

Max Activating Token Index: 709

Text #12

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.8265. Min Act: -0.0000

Data Index: 275184 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.7336. Min Act: -0.0000

Data Index: 463897 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1555568 (Python Code)

Max Activating Token Index: 885

Text #15

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.8469. Min Act: -0.0000

Data Index: 209089 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.8504. Min Act: -0.0000

Data Index: 535438 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.8462. Min Act: -0.0000

Data Index: 798312 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.7954. Min Act: -0.0000

Data Index: 671746 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.8179. Min Act: -0.0000

Data Index: 744382 (C4 (Web Text))

Max Activating Token Index: 79