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

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

Neuron 36 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.6820. Min Act: -0.0002

Data Index: 143560 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.5189. Min Act: -0.0002

Data Index: 289997 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4914. Min Act: -0.0002

Data Index: 933749 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4786. Min Act: -0.0002

Data Index: 365942 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4633. Min Act: -0.0002

Data Index: 436666 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4748. Min Act: -0.0002

Data Index: 371365 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4590. Min Act: -0.0002

Data Index: 1077311 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4718. Min Act: -0.0002

Data Index: 662764 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.5132. Min Act: -0.0002

Data Index: 1018622 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4688. Min Act: -0.0002

Data Index: 1171448 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.4390. Min Act: -0.0002

Data Index: 927035 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.3839. Min Act: -0.0002

Data Index: 1063277 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.3439. Min Act: -0.0002

Data Index: 662761 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.3308. Min Act: -0.0002

Data Index: 343048 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.3922. Min Act: -0.0002

Data Index: 1198249 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.3797. Min Act: -0.0002

Data Index: 294663 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.3997. Min Act: -0.0002

Data Index: 779986 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.3995. Min Act: -0.0002

Data Index: 740611 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.3843. Min Act: -0.0002

Data Index: 932697 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.6820. Min Range: -0.6820

Max Act: 0.3688. Min Act: -0.0002

Data Index: 1177721 (C4 (Web Text))

Max Activating Token Index: 216