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

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

Neuron 2462 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: 0.5845. Min Range: -0.5845

Max Act: 0.5845. Min Act: -0.0000

Data Index: 1225867 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5795. Min Act: -0.0000

Data Index: 625575 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5653. Min Act: -0.0000

Data Index: 550962 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1243975 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4737. Min Act: -0.0000

Data Index: 21109 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1345586 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4398. Min Act: -0.0000

Data Index: 804395 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1199482 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1143102 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4541. Min Act: -0.0000

Data Index: 423845 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4346. Min Act: -0.0000

Data Index: 598343 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4195. Min Act: -0.0000

Data Index: 982692 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4309. Min Act: -0.0000

Data Index: 410916 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4317. Min Act: -0.0000

Data Index: 540551 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4270. Min Act: -0.0000

Data Index: 497481 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4267. Min Act: -0.0000

Data Index: 355121 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4109. Min Act: -0.0000

Data Index: 743814 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1006039 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1052535 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4001. Min Act: -0.0000

Data Index: 287979 (C4 (Web Text))

Max Activating Token Index: 93