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

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

Neuron 5006 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: 0.1141. Min Range: -0.1141

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1034020 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1131. Min Act: -0.0002

Data Index: 282281 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0860. Min Act: -0.0002

Data Index: 865669 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0828. Min Act: -0.0002

Data Index: 248390 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0799. Min Act: -0.0002

Data Index: 120145 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1278141 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1059700 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0718. Min Act: -0.0002

Data Index: 741860 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0797. Min Act: -0.0002

Data Index: 21376 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1254974 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1353214 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0805. Min Act: -0.0002

Data Index: 410193 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0664. Min Act: -0.0002

Data Index: 644932 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1305022 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0735. Min Act: -0.0002

Data Index: 872696 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0764. Min Act: -0.0002

Data Index: 627792 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0655. Min Act: -0.0002

Data Index: 317496 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0717. Min Act: -0.0002

Data Index: 278102 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1120425 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0748. Min Act: -0.0002

Data Index: 539388 (C4 (Web Text))

Max Activating Token Index: 50