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

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

Neuron 5503 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: 2.5807. Min Range: -2.5807

Max Act: 2.5807. Min Act: -0.0001

Data Index: 587118 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.4014. Min Act: -0.0001

Data Index: 1340694 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.3839. Min Act: -0.0001

Data Index: 588673 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.3393. Min Act: -0.0001

Data Index: 1007251 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.2948. Min Act: -0.0001

Data Index: 96086 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.1519. Min Act: -0.0001

Data Index: 354294 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.1192. Min Act: -0.0001

Data Index: 479295 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.1160. Min Act: -0.0001

Data Index: 666949 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.0927. Min Act: -0.0001

Data Index: 1277760 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.0801. Min Act: -0.0001

Data Index: 728475 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.0777. Min Act: -0.0001

Data Index: 240964 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.0666. Min Act: -0.0001

Data Index: 1204156 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.0751. Min Act: -0.0001

Data Index: 954289 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.0618. Min Act: -0.0001

Data Index: 1245450 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.0471. Min Act: -0.0001

Data Index: 608000 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.0367. Min Act: -0.0001

Data Index: 1150423 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.0316. Min Act: -0.0001

Data Index: 337667 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.0497. Min Act: -0.0001

Data Index: 455283 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.0575. Min Act: -0.0001

Data Index: 91311 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 2.5807. Min Range: -2.5807

Max Act: 2.0308. Min Act: -0.0001

Data Index: 495512 (C4 (Web Text))

Max Activating Token Index: 1023