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

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

Neuron 3735 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.8424. Min Act: -0.0001

Data Index: 1338431 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.8081. Min Act: -0.0001

Data Index: 74397 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.8046. Min Act: -0.0001

Data Index: 1000388 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.8122. Min Act: -0.0001

Data Index: 1345855 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.7130. Min Act: -0.0001

Data Index: 525499 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.6287. Min Act: -0.0001

Data Index: 1092008 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.6669. Min Act: -0.0001

Data Index: 577820 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.7829. Min Act: -0.0001

Data Index: 87603 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.6936. Min Act: -0.0001

Data Index: 1346121 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.7025. Min Act: -0.0001

Data Index: 277443 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.6909. Min Act: -0.0001

Data Index: 304003 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.6311. Min Act: -0.0001

Data Index: 461254 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.7232. Min Act: -0.0001

Data Index: 504074 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.4377. Min Act: -0.0001

Data Index: 256337 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.6714. Min Act: -0.0001

Data Index: 1156226 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.6945. Min Act: -0.0001

Data Index: 383964 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.6724. Min Act: -0.0001

Data Index: 144551 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.6850. Min Act: -0.0001

Data Index: 1338455 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.6388. Min Act: -0.0001

Data Index: 1318069 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 1.8424. Min Range: -1.8424

Max Act: 1.5725. Min Act: -0.0001

Data Index: 1127156 (C4 (Web Text))

Max Activating Token Index: 687