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

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

Neuron 51 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.0784. Min Act: -0.0000

Data Index: 373165 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1015338 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.1843. Min Act: -0.0000

Data Index: 894875 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1343873 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.0988. Min Act: -0.0000

Data Index: 989825 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.1554. Min Act: -0.0000

Data Index: 632734 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.2101. Min Act: -0.0000

Data Index: 1143589 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.1318. Min Act: -0.0000

Data Index: 941326 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.9862. Min Act: -0.0000

Data Index: 100481 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.1056. Min Act: -0.0000

Data Index: 1232014 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.0293. Min Act: -0.0000

Data Index: 590956 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.0094. Min Act: -0.0000

Data Index: 1221122 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.9854. Min Act: -0.0000

Data Index: 1344976 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8857. Min Act: -0.0000

Data Index: 266416 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.9229. Min Act: -0.0000

Data Index: 881247 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.9007. Min Act: -0.0000

Data Index: 426442 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.9035. Min Act: -0.0000

Data Index: 1359321 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8795. Min Act: -0.0000

Data Index: 1130796 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8191. Min Act: -0.0000

Data Index: 954234 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.8714. Min Act: -0.0000

Data Index: 465832 (C4 (Web Text))

Max Activating Token Index: 685