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

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

Neuron 2356 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0754. Min Range: -1.0754

Max Act: 1.0754. Min Act: -0.0000

Data Index: 181665 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 1.0754. Min Range: -1.0754

Max Act: 1.0037. Min Act: -0.0000

Data Index: 1013894 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.9544. Min Act: -0.0000

Data Index: 536438 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8879. Min Act: -0.0000

Data Index: 968204 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.9484. Min Act: -0.0000

Data Index: 961987 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8740. Min Act: -0.0000

Data Index: 245548 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8919. Min Act: -0.0000

Data Index: 1157654 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8618. Min Act: -0.0000

Data Index: 544193 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8832. Min Act: -0.0000

Data Index: 67148 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8528. Min Act: -0.0000

Data Index: 172963 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1326811 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8189. Min Act: -0.0000

Data Index: 259834 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1334921 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1199282 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7843. Min Act: -0.0000

Data Index: 1249327 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1371525 (Python Code)

Max Activating Token Index: 722

Text #16

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7564. Min Act: -0.0000

Data Index: 566541 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7786. Min Act: -0.0000

Data Index: 774819 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1303927 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7760. Min Act: -0.0000

Data Index: 587444 (C4 (Web Text))

Max Activating Token Index: 964