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

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

Neuron 223 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.9785. Min Act: -0.0000

Data Index: 953961 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.7368. Min Act: -0.0000

Data Index: 429520 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6947. Min Act: -0.0000

Data Index: 161106 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.7640. Min Act: -0.0000

Data Index: 177052 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.7605. Min Act: -0.0000

Data Index: 925650 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1196661 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6176. Min Act: -0.0000

Data Index: 890709 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6473. Min Act: -0.0000

Data Index: 534218 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6374. Min Act: -0.0000

Data Index: 223515 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6322. Min Act: -0.0000

Data Index: 436114 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6202. Min Act: -0.0000

Data Index: 305755 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6201. Min Act: -0.0000

Data Index: 249022 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6153. Min Act: -0.0000

Data Index: 548725 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1265426 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6144. Min Act: -0.0000

Data Index: 151394 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1302668 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.5702. Min Act: -0.0000

Data Index: 641333 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6070. Min Act: -0.0000

Data Index: 770321 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6060. Min Act: -0.0000

Data Index: 78808 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1100792 (C4 (Web Text))

Max Activating Token Index: 967