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

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

Neuron 1048 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.5804. Min Act: -0.0000

Data Index: 5967 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.6170. Min Act: -0.0000

Data Index: 447267 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.6273. Min Act: -0.0000

Data Index: 366816 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.4958. Min Act: -0.0000

Data Index: 309405 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.4943. Min Act: -0.0000

Data Index: 627653 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.4858. Min Act: -0.0000

Data Index: 747687 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.4974. Min Act: -0.0000

Data Index: 419752 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.4676. Min Act: -0.0000

Data Index: 972648 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1037715 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.4134. Min Act: -0.0000

Data Index: 134073 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.3800. Min Act: -0.0000

Data Index: 70436 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.4096. Min Act: -0.0000

Data Index: 179639 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.4240. Min Act: -0.0000

Data Index: 807313 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1057328 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.3891. Min Act: -0.0000

Data Index: 305385 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.4296. Min Act: -0.0000

Data Index: 950195 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.3996. Min Act: -0.0000

Data Index: 518032 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1117855 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.5220. Min Act: -0.0000

Data Index: 737910 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.6273. Min Range: -0.6273

Max Act: 0.4625. Min Act: -0.0000

Data Index: 806759 (C4 (Web Text))

Max Activating Token Index: 283