Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 422 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.9972. Min Act: -0.0000

Data Index: 49424 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.9836. Min Act: -0.0001

Data Index: 377125 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.9250. Min Act: -0.0001

Data Index: 258326 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.9126. Min Act: -0.0001

Data Index: 888778 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.8982. Min Act: -0.0001

Data Index: 833839 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.8313. Min Act: -0.0001

Data Index: 818929 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.8410. Min Act: 0.0001

Data Index: 830025 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.8295. Min Act: -0.0001

Data Index: 810501 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.8144. Min Act: -0.0001

Data Index: 959744 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.8235. Min Act: -0.0001

Data Index: 588580 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.7911. Min Act: 0.0000

Data Index: 434677 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.8093. Min Act: -0.0000

Data Index: 430136 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.7690. Min Act: -0.0001

Data Index: 203912 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.7917. Min Act: -0.0001

Data Index: 224148 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.7907. Min Act: -0.0001

Data Index: 668557 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.7887. Min Act: 0.0001

Data Index: 685108 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.7621. Min Act: -0.0001

Data Index: 249826 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.7835. Min Act: -0.0001

Data Index: 1322736 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.8502. Min Act: 0.0001

Data Index: 991126 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.8183. Min Act: -0.0001

Data Index: 995113 (C4 (Web Text))

Max Activating Token Index: 106