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

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

Neuron 3531 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1186. Min Act: -0.0000

Data Index: 1016438 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0978. Min Act: -0.0000

Data Index: 298070 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1197228 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1282984 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1115329 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0873. Min Act: -0.0000

Data Index: 626915 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0805. Min Act: -0.0000

Data Index: 819474 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0791. Min Act: -0.0000

Data Index: 600085 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0790. Min Act: -0.0000

Data Index: 750753 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0785. Min Act: -0.0000

Data Index: 219627 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0809. Min Act: -0.0000

Data Index: 438695 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0795. Min Act: -0.0000

Data Index: 853701 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0766. Min Act: -0.0000

Data Index: 283727 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0783. Min Act: -0.0000

Data Index: 335067 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1153531 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0778. Min Act: -0.0000

Data Index: 947344 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0739. Min Act: -0.0000

Data Index: 200676 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0722. Min Act: -0.0000

Data Index: 1012890 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0773. Min Act: -0.0000

Data Index: 417282 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0740. Min Act: -0.0000

Data Index: 1033954 (C4 (Web Text))

Max Activating Token Index: 609