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

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

Neuron 6049 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: 1.0589. Min Range: -1.0589

Max Act: 1.0589. Min Act: -0.0001

Data Index: 467831 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0529. Min Act: -0.0001

Data Index: 610186 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0220. Min Act: -0.0001

Data Index: 293170 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0006. Min Act: -0.0001

Data Index: 294872 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0088. Min Act: -0.0001

Data Index: 1166808 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9955. Min Act: -0.0001

Data Index: 20903 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0086. Min Act: -0.0001

Data Index: 42415 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9978. Min Act: -0.0001

Data Index: 930352 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9918. Min Act: -0.0002

Data Index: 1249978 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9873. Min Act: -0.0001

Data Index: 529694 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9947. Min Act: -0.0001

Data Index: 1300539 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0044. Min Act: -0.0001

Data Index: 741512 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9862. Min Act: -0.0001

Data Index: 53026 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9961. Min Act: -0.0001

Data Index: 1282125 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9861. Min Act: -0.0001

Data Index: 368258 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0053. Min Act: -0.0001

Data Index: 545761 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9939. Min Act: -0.0001

Data Index: 208296 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9975. Min Act: -0.0001

Data Index: 842438 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9920. Min Act: -0.0001

Data Index: 250629 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9986. Min Act: -0.0001

Data Index: 909212 (C4 (Web Text))

Max Activating Token Index: 1023