Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2390 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.9731. Min Act: -0.0001

Data Index: 1264375 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.9671. Min Act: -0.0002

Data Index: 67528 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8455. Min Act: -0.0002

Data Index: 417061 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.9254. Min Act: -0.0001

Data Index: 674007 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8922. Min Act: -0.0002

Data Index: 1035324 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8964. Min Act: -0.0002

Data Index: 334349 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8869. Min Act: -0.0002

Data Index: 960216 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.9400. Min Act: -0.0002

Data Index: 930815 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8182. Min Act: -0.0002

Data Index: 402988 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8801. Min Act: -0.0001

Data Index: 1434425 (Python Code)

Max Activating Token Index: 86

Text #10

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8796. Min Act: -0.0002

Data Index: 795162 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.9114. Min Act: -0.0002

Data Index: 1220898 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8744. Min Act: -0.0001

Data Index: 47863 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8201. Min Act: -0.0002

Data Index: 851414 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8427. Min Act: -0.0002

Data Index: 1281383 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8151. Min Act: -0.0002

Data Index: 769119 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8815. Min Act: -0.0002

Data Index: 511715 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8265. Min Act: -0.0002

Data Index: 875102 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8433. Min Act: -0.0002

Data Index: 1353313 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8221. Min Act: -0.0002

Data Index: 166631 (C4 (Web Text))

Max Activating Token Index: 949