Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1472 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0010. Min Act: -0.0006

Data Index: 964933 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0009. Min Act: -0.0007

Data Index: 1038884 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0009. Min Act: -0.0006

Data Index: 1343811 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0009. Min Act: -0.0006

Data Index: 792427 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0009. Min Act: -0.0006

Data Index: 649868 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0009. Min Act: -0.0006

Data Index: 547312 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0009. Min Act: -0.0006

Data Index: 1145758 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0009. Min Act: -0.0006

Data Index: 517674 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0009. Min Act: -0.0006

Data Index: 920026 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0008. Min Act: -0.0006

Data Index: 885857 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0009. Min Act: -0.0006

Data Index: 777511 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0008. Min Act: -0.0006

Data Index: 1117639 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0008. Min Act: -0.0006

Data Index: 844399 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0008. Min Act: -0.0006

Data Index: 176757 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0008. Min Act: -0.0006

Data Index: 20371 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0008. Min Act: -0.0006

Data Index: 285812 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0008. Min Act: -0.0006

Data Index: 1263853 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0008. Min Act: -0.0006

Data Index: 141932 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0008. Min Act: -0.0007

Data Index: 613177 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0008. Min Act: -0.0006

Data Index: 1242422 (C4 (Web Text))

Max Activating Token Index: 133