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

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

Neuron 2442 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3561. Min Range: -3.3561

Max Act: 3.3561. Min Act: -0.0000

Data Index: 324018 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 3.3561. Min Range: -3.3561

Max Act: 2.9235. Min Act: -0.0000

Data Index: 264595 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 3.3561. Min Range: -3.3561

Max Act: 2.9109. Min Act: -0.0000

Data Index: 533842 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 3.3561. Min Range: -3.3561

Max Act: 2.8258. Min Act: -0.0000

Data Index: 495265 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 3.3561. Min Range: -3.3561

Max Act: 2.6278. Min Act: -0.0000

Data Index: 741544 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 3.3561. Min Range: -3.3561

Max Act: 2.4748. Min Act: -0.0000

Data Index: 226702 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 3.3561. Min Range: -3.3561

Max Act: 2.1678. Min Act: -0.0000

Data Index: 1239286 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 3.3561. Min Range: -3.3561

Max Act: 2.4000. Min Act: -0.0000

Data Index: 828840 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 3.3561. Min Range: -3.3561

Max Act: 2.0992. Min Act: -0.0000

Data Index: 704272 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 3.3561. Min Range: -3.3561

Max Act: 1.9846. Min Act: -0.0000

Data Index: 419600 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 3.3561. Min Range: -3.3561

Max Act: 1.6668. Min Act: -0.0000

Data Index: 89124 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 3.3561. Min Range: -3.3561

Max Act: 1.5242. Min Act: -0.0000

Data Index: 440382 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 3.3561. Min Range: -3.3561

Max Act: 1.7680. Min Act: -0.0000

Data Index: 936867 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 3.3561. Min Range: -3.3561

Max Act: 1.6241. Min Act: -0.0000

Data Index: 634154 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 3.3561. Min Range: -3.3561

Max Act: 1.5647. Min Act: -0.0000

Data Index: 31747 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 3.3561. Min Range: -3.3561

Max Act: 1.5268. Min Act: -0.0000

Data Index: 628893 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 3.3561. Min Range: -3.3561

Max Act: 1.4623. Min Act: -0.0000

Data Index: 1313304 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 3.3561. Min Range: -3.3561

Max Act: 1.2670. Min Act: -0.0000

Data Index: 646814 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 3.3561. Min Range: -3.3561

Max Act: 1.4564. Min Act: -0.0000

Data Index: 1468874 (Python Code)

Max Activating Token Index: 449

Text #19

Max Range: 3.3561. Min Range: -3.3561

Max Act: 1.3668. Min Act: -0.0000

Data Index: 1124733 (C4 (Web Text))

Max Activating Token Index: 273