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

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

Neuron 1777 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7682. Min Act: -0.0000

Data Index: 683609 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7402. Min Act: -0.0000

Data Index: 170990 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7832. Min Act: -0.0000

Data Index: 272699 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1087013 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1249225 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1169580 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7332. Min Act: -0.0000

Data Index: 507644 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6828. Min Act: -0.0000

Data Index: 68886 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7021. Min Act: -0.0000

Data Index: 892389 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7164. Min Act: -0.0000

Data Index: 576278 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1341412 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7135. Min Act: -0.0000

Data Index: 299219 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7043. Min Act: -0.0000

Data Index: 144182 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1102853 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6232. Min Act: -0.0000

Data Index: 637786 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6658. Min Act: -0.0000

Data Index: 574923 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6193. Min Act: -0.0001

Data Index: 985898 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6232. Min Act: -0.0000

Data Index: 849790 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7100. Min Act: -0.0000

Data Index: 73090 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1341257 (C4 (Web Text))

Max Activating Token Index: 75