Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1460 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.4177. Min Act: -0.0001

Data Index: 512503 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.4137. Min Act: -0.0001

Data Index: 1209176 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.4024. Min Act: -0.0001

Data Index: 1263785 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.4042. Min Act: -0.0001

Data Index: 88180 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3641. Min Act: -0.0001

Data Index: 496078 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3894. Min Act: -0.0001

Data Index: 404585 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3720. Min Act: -0.0001

Data Index: 250180 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3789. Min Act: -0.0001

Data Index: 239306 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3649. Min Act: -0.0001

Data Index: 990018 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3519. Min Act: -0.0001

Data Index: 662897 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3366. Min Act: -0.0001

Data Index: 458269 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3596. Min Act: -0.0001

Data Index: 1136717 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3572. Min Act: -0.0001

Data Index: 1180819 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3209. Min Act: -0.0001

Data Index: 753078 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3250. Min Act: -0.0001

Data Index: 112251 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3377. Min Act: -0.0001

Data Index: 313335 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3016. Min Act: -0.0001

Data Index: 215978 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.3683. Min Act: -0.0001

Data Index: 696966 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.2904. Min Act: -0.0001

Data Index: 71934 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.4177. Min Range: -0.4177

Max Act: 0.2904. Min Act: -0.0001

Data Index: 311008 (C4 (Web Text))

Max Activating Token Index: 497