Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 388 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.2173. Min Act: -0.0005

Data Index: 883362 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.2055. Min Act: -0.0005

Data Index: 1333855 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1980. Min Act: -0.0005

Data Index: 630130 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.2011. Min Act: -0.0005

Data Index: 362330 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1915. Min Act: -0.0005

Data Index: 1094515 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1818. Min Act: -0.0005

Data Index: 658521 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1806. Min Act: -0.0005

Data Index: 1077004 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1771. Min Act: -0.0005

Data Index: 467970 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1737. Min Act: -0.0005

Data Index: 1165149 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1708. Min Act: -0.0005

Data Index: 19016 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1824. Min Act: -0.0005

Data Index: 577037 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1744. Min Act: -0.0005

Data Index: 340194 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1665. Min Act: -0.0005

Data Index: 1078386 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1567. Min Act: -0.0005

Data Index: 499809 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1721. Min Act: -0.0005

Data Index: 204476 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1706. Min Act: -0.0005

Data Index: 861041 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1656. Min Act: -0.0005

Data Index: 726941 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1598. Min Act: -0.0005

Data Index: 733850 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1693. Min Act: -0.0005

Data Index: 87052 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1594. Min Act: -0.0005

Data Index: 689922 (C4 (Web Text))

Max Activating Token Index: 760