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

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

Neuron 3181 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: 1.5840. Min Range: -1.5840

Max Act: 1.5840. Min Act: -0.0000

Data Index: 427254 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.2678. Min Act: -0.0000

Data Index: 930465 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.4623. Min Act: -0.0000

Data Index: 1003490 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.1124. Min Act: -0.0000

Data Index: 145736 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.1693. Min Act: -0.0000

Data Index: 148432 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0687. Min Act: -0.0000

Data Index: 939337 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0813. Min Act: -0.0000

Data Index: 321533 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.1650. Min Act: -0.0000

Data Index: 945905 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.1170. Min Act: -0.0000

Data Index: 857233 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 1.5840. Min Range: -1.5840

Max Act: 0.9959. Min Act: -0.0000

Data Index: 987395 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0415. Min Act: -0.0000

Data Index: 224986 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0531. Min Act: -0.0000

Data Index: 873082 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0137. Min Act: -0.0000

Data Index: 672792 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0785. Min Act: -0.0000

Data Index: 390356 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 1.5840. Min Range: -1.5840

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1217359 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0599. Min Act: -0.0000

Data Index: 1142157 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1257884 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 1.5840. Min Range: -1.5840

Max Act: 0.9785. Min Act: -0.0000

Data Index: 331248 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0248. Min Act: -0.0000

Data Index: 785544 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.0038. Min Act: -0.0000

Data Index: 748620 (C4 (Web Text))

Max Activating Token Index: 11