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

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

Neuron 62 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.6102. Min Act: -0.0000

Data Index: 423017 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.5947. Min Act: -0.0001

Data Index: 449484 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.5493. Min Act: -0.0001

Data Index: 246325 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.5486. Min Act: -0.0000

Data Index: 862992 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.5277. Min Act: -0.0000

Data Index: 8674 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.5200. Min Act: -0.0000

Data Index: 989529 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.5208. Min Act: -0.0001

Data Index: 840273 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.5174. Min Act: -0.0000

Data Index: 787915 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.5184. Min Act: -0.0000

Data Index: 738629 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1280583 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.5069. Min Act: -0.0000

Data Index: 950350 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.5200. Min Act: -0.0000

Data Index: 979900 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1133733 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.5005. Min Act: 0.0000

Data Index: 619687 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.4817. Min Act: -0.0000

Data Index: 39815 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.4983. Min Act: -0.0001

Data Index: 81527 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.4543. Min Act: -0.0000

Data Index: 874514 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.4768. Min Act: -0.0000

Data Index: 967558 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1051617 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.6102. Min Range: -0.6102

Max Act: 0.4641. Min Act: -0.0000

Data Index: 503988 (C4 (Web Text))

Max Activating Token Index: 937