Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 957 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0304. Min Range: -2.0304

Max Act: 2.0201. Min Act: -0.0000

Data Index: 863431 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.9438. Min Act: -0.0000

Data Index: 428789 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.9918. Min Act: -0.0000

Data Index: 97310 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 2.0304. Min Range: -2.0304

Max Act: 2.0304. Min Act: -0.0000

Data Index: 1001122 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.8304. Min Act: -0.0000

Data Index: 1004852 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.8105. Min Act: -0.0000

Data Index: 346106 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.9039. Min Act: -0.0000

Data Index: 168045 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.7996. Min Act: -0.0000

Data Index: 924946 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.7807. Min Act: -0.0000

Data Index: 737701 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.7217. Min Act: -0.0000

Data Index: 741753 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.7100. Min Act: -0.0000

Data Index: 356055 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.8020. Min Act: -0.0000

Data Index: 578828 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.6841. Min Act: -0.0000

Data Index: 231602 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.7641. Min Act: -0.0000

Data Index: 359863 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.7627. Min Act: -0.0000

Data Index: 402564 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.6612. Min Act: -0.0000

Data Index: 1290786 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.6722. Min Act: -0.0000

Data Index: 863566 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.6231. Min Act: -0.0000

Data Index: 119477 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.6173. Min Act: -0.0000

Data Index: 432788 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 2.0304. Min Range: -2.0304

Max Act: 1.5230. Min Act: -0.0000

Data Index: 96536 (C4 (Web Text))

Max Activating Token Index: 659