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

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

Neuron 574 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.3067. Min Act: -0.0000

Data Index: 335999 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2677. Min Act: -0.0000

Data Index: 828769 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1167775 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2466. Min Act: -0.0000

Data Index: 620877 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2394. Min Act: -0.0000

Data Index: 336970 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2181. Min Act: -0.0000

Data Index: 869149 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2117. Min Act: -0.0000

Data Index: 828302 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1308808 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2071. Min Act: -0.0000

Data Index: 419467 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1993. Min Act: -0.0000

Data Index: 644604 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2059. Min Act: -0.0000

Data Index: 652291 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1878. Min Act: -0.0000

Data Index: 157398 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2148. Min Act: -0.0000

Data Index: 67211 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1716. Min Act: -0.0000

Data Index: 475071 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1723. Min Act: -0.0000

Data Index: 179897 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1768. Min Act: -0.0000

Data Index: 795373 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1703. Min Act: -0.0000

Data Index: 1079381 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1660. Min Act: -0.0000

Data Index: 1174772 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1030120 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1133131 (C4 (Web Text))

Max Activating Token Index: 232