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

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

Neuron 3491 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1761. Min Range: -1.1761

Max Act: 1.1761. Min Act: -0.0001

Data Index: 997561 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.8798. Min Act: -0.0001

Data Index: 1076770 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.9182. Min Act: -0.0001

Data Index: 381536 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.8859. Min Act: -0.0001

Data Index: 797785 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.7688. Min Act: -0.0001

Data Index: 31067 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.6806. Min Act: -0.0001

Data Index: 479548 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.7868. Min Act: -0.0001

Data Index: 974563 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.6967. Min Act: -0.0001

Data Index: 1256746 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.8856. Min Act: -0.0001

Data Index: 1104135 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.9359. Min Act: -0.0001

Data Index: 1226278 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.7969. Min Act: -0.0001

Data Index: 550901 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.8105. Min Act: -0.0001

Data Index: 1149172 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.7567. Min Act: -0.0001

Data Index: 271255 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.8551. Min Act: -0.0001

Data Index: 1274912 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.7918. Min Act: -0.0001

Data Index: 319120 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.8562. Min Act: -0.0001

Data Index: 166916 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.8561. Min Act: -0.0001

Data Index: 606141 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.8204. Min Act: -0.0001

Data Index: 140988 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.7732. Min Act: -0.0001

Data Index: 862299 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.7883. Min Act: -0.0001

Data Index: 742728 (C4 (Web Text))

Max Activating Token Index: 828