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

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

Neuron 5646 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.9751. Min Act: -0.0001

Data Index: 189559 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.9267. Min Act: -0.0001

Data Index: 257944 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.9295. Min Act: -0.0001

Data Index: 958113 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.6356. Min Act: -0.0001

Data Index: 246076 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.7697. Min Act: -0.0001

Data Index: 978488 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.8445. Min Act: -0.0001

Data Index: 1083599 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.7438. Min Act: -0.0001

Data Index: 578665 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.9815. Min Act: -0.0001

Data Index: 156879 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.6182. Min Act: -0.0001

Data Index: 544226 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.8879. Min Act: -0.0001

Data Index: 34212 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.6633. Min Act: -0.0001

Data Index: 490497 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.7027. Min Act: -0.0001

Data Index: 1178676 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.7135. Min Act: -0.0001

Data Index: 353215 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.9234. Min Act: -0.0001

Data Index: 162455 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.5267. Min Act: -0.0001

Data Index: 660768 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.5878. Min Act: -0.0001

Data Index: 373054 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.7186. Min Act: -0.0001

Data Index: 596713 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.5926. Min Act: -0.0001

Data Index: 78669 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.5675. Min Act: -0.0001

Data Index: 1153067 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.4808. Min Act: -0.0001

Data Index: 67888 (C4 (Web Text))

Max Activating Token Index: 781