Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 52 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2230. Min Act: -0.0003

Data Index: 1067737 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2441. Min Act: -0.0003

Data Index: 686346 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2220. Min Act: -0.0003

Data Index: 182689 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1913. Min Act: -0.0003

Data Index: 1207444 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2030. Min Act: -0.0003

Data Index: 1027375 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2229. Min Act: -0.0003

Data Index: 278605 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2076. Min Act: -0.0003

Data Index: 1024182 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2132. Min Act: -0.0003

Data Index: 653713 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1992. Min Act: -0.0003

Data Index: 498177 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1854. Min Act: -0.0003

Data Index: 967852 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1742. Min Act: -0.0003

Data Index: 782099 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1657. Min Act: -0.0003

Data Index: 138203 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1864. Min Act: -0.0003

Data Index: 1236156 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1761. Min Act: -0.0003

Data Index: 373631 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1831. Min Act: -0.0003

Data Index: 1034631 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1643. Min Act: -0.0003

Data Index: 300957 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1730. Min Act: -0.0003

Data Index: 1314902 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1844. Min Act: -0.0003

Data Index: 788832 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1858. Min Act: -0.0003

Data Index: 1094122 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1589. Min Act: -0.0003

Data Index: 866009 (C4 (Web Text))

Max Activating Token Index: 647