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

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

Neuron 5907 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: 0.6738. Min Range: -0.6738

Max Act: 0.6738. Min Act: -0.0000

Data Index: 54660 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1281640 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4617. Min Act: -0.0000

Data Index: 564196 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4787. Min Act: -0.0000

Data Index: 919874 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1354944 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4154. Min Act: -0.0000

Data Index: 716299 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4213. Min Act: -0.0000

Data Index: 754967 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1346945 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4056. Min Act: -0.0000

Data Index: 722489 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.3889. Min Act: -0.0000

Data Index: 538330 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1160781 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4272. Min Act: -0.0000

Data Index: 573847 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.3947. Min Act: -0.0000

Data Index: 376274 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4076. Min Act: -0.0000

Data Index: 1018859 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1168966 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1119824 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1120529 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.3927. Min Act: -0.0000

Data Index: 283147 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1101858 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4015. Min Act: -0.0000

Data Index: 602796 (C4 (Web Text))

Max Activating Token Index: 208