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

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

Neuron 3088 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 831337 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 945682 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 475021 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 781965 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 135962 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1166966 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 762997 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 525812 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1158031 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 329578 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1029739 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1446575 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1241278 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 744423 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 732294 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 89901 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 393124 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1019218 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 24473 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 639522 (C4 (Web Text))

Max Activating Token Index: 1023