Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 600 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1154. Min Act: -0.0002

Data Index: 609477 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0967. Min Act: -0.0002

Data Index: 946801 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0895. Min Act: -0.0002

Data Index: 869974 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0954. Min Act: -0.0002

Data Index: 200923 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1331780 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0878. Min Act: -0.0002

Data Index: 26226 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0837. Min Act: -0.0002

Data Index: 228349 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0878. Min Act: -0.0002

Data Index: 577265 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0806. Min Act: -0.0002

Data Index: 931156 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0824. Min Act: -0.0002

Data Index: 182884 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1161810 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0897. Min Act: -0.0002

Data Index: 117151 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0856. Min Act: -0.0002

Data Index: 307939 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1283239 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0914. Min Act: -0.0002

Data Index: 659369 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1098137 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1285364 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0824. Min Act: -0.0002

Data Index: 696520 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1359720 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1043 (C4 (Web Text))

Max Activating Token Index: 400