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

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

Neuron 3963 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2014. Min Range: -2.2014

Max Act: 2.2014. Min Act: -0.0000

Data Index: 463399 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 2.2014. Min Range: -2.2014

Max Act: 2.0165. Min Act: -0.0000

Data Index: 803053 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.9096. Min Act: -0.0000

Data Index: 1349360 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.7888. Min Act: -0.0000

Data Index: 58351 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.8649. Min Act: -0.0000

Data Index: 795732 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.8005. Min Act: -0.0000

Data Index: 836340 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.7903. Min Act: -0.0000

Data Index: 642607 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.7975. Min Act: -0.0000

Data Index: 364342 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.8755. Min Act: -0.0000

Data Index: 232818 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.7344. Min Act: -0.0000

Data Index: 507162 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.7100. Min Act: -0.0000

Data Index: 327437 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.7236. Min Act: -0.0000

Data Index: 825157 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.6942. Min Act: -0.0000

Data Index: 356904 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.7011. Min Act: -0.0000

Data Index: 862184 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.6978. Min Act: -0.0000

Data Index: 240215 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.6065. Min Act: -0.0000

Data Index: 320233 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.6924. Min Act: -0.0000

Data Index: 965560 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.6270. Min Act: -0.0000

Data Index: 1361658 (Python Code)

Max Activating Token Index: 292

Text #18

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.6811. Min Act: -0.0000

Data Index: 881209 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 2.2014. Min Range: -2.2014

Max Act: 1.6669. Min Act: -0.0000

Data Index: 597948 (C4 (Web Text))

Max Activating Token Index: 102