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

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

Neuron 3440 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: 2.2192. Min Range: -2.2192

Max Act: 2.2192. Min Act: -0.0000

Data Index: 270992 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 2.2192. Min Range: -2.2192

Max Act: 2.0883. Min Act: -0.0000

Data Index: 1158980 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 2.2192. Min Range: -2.2192

Max Act: 2.0357. Min Act: -0.0000

Data Index: 304810 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.8977. Min Act: -0.0000

Data Index: 63595 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.9514. Min Act: -0.0000

Data Index: 575590 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.6829. Min Act: -0.0000

Data Index: 540196 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.8522. Min Act: -0.0000

Data Index: 1113917 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.5705. Min Act: -0.0000

Data Index: 55874 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.7725. Min Act: -0.0000

Data Index: 808047 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.8963. Min Act: -0.0000

Data Index: 525452 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.6529. Min Act: -0.0000

Data Index: 805131 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.4712. Min Act: -0.0000

Data Index: 995744 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.5394. Min Act: -0.0000

Data Index: 719687 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.6288. Min Act: -0.0000

Data Index: 692352 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.4534. Min Act: -0.0000

Data Index: 911840 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.4970. Min Act: -0.0000

Data Index: 561895 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.4067. Min Act: -0.0000

Data Index: 1303252 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.4127. Min Act: -0.0000

Data Index: 281721 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.5737. Min Act: -0.0000

Data Index: 491137 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 2.2192. Min Range: -2.2192

Max Act: 1.3080. Min Act: -0.0000

Data Index: 533425 (C4 (Web Text))

Max Activating Token Index: 255