Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5363 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.7281. Min Act: -0.0001

Data Index: 467689 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.7247. Min Act: -0.0001

Data Index: 987676 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.7040. Min Act: -0.0001

Data Index: 117371 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.7084. Min Act: -0.0002

Data Index: 561988 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6961. Min Act: -0.0001

Data Index: 673323 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6880. Min Act: -0.0001

Data Index: 1027085 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6813. Min Act: -0.0001

Data Index: 1269119 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6941. Min Act: -0.0001

Data Index: 1210632 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6765. Min Act: -0.0001

Data Index: 143122 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6765. Min Act: -0.0001

Data Index: 775923 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6840. Min Act: -0.0001

Data Index: 747143 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6821. Min Act: -0.0002

Data Index: 1300748 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6802. Min Act: -0.0001

Data Index: 763882 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6771. Min Act: -0.0001

Data Index: 648943 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6645. Min Act: -0.0001

Data Index: 103920 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6603. Min Act: -0.0001

Data Index: 172160 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6742. Min Act: -0.0001

Data Index: 901150 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6639. Min Act: -0.0001

Data Index: 764415 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6568. Min Act: -0.0001

Data Index: 54749 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6545. Min Act: -0.0001

Data Index: 578713 (C4 (Web Text))

Max Activating Token Index: 12