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

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

Neuron 5136 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.7765. Min Act: -0.0000

Data Index: 1131325 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.2522. Min Act: -0.0000

Data Index: 428346 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.2116. Min Act: -0.0000

Data Index: 465093 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.3170. Min Act: -0.0000

Data Index: 1244 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.2069. Min Act: -0.0000

Data Index: 569138 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.1589. Min Act: -0.0000

Data Index: 380334 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.1798. Min Act: -0.0000

Data Index: 1068492 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.0643. Min Act: -0.0000

Data Index: 867226 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.0426. Min Act: -0.0000

Data Index: 514559 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.0833. Min Act: -0.0000

Data Index: 926330 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.0819. Min Act: -0.0000

Data Index: 107628 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.0356. Min Act: -0.0000

Data Index: 424250 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.0586. Min Act: -0.0000

Data Index: 294564 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.0424. Min Act: -0.0000

Data Index: 658868 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.0486. Min Act: -0.0000

Data Index: 629686 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 1.7765. Min Range: -1.7765

Max Act: 0.9681. Min Act: -0.0000

Data Index: 1029921 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.0365. Min Act: -0.0000

Data Index: 400141 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.0445. Min Act: -0.0000

Data Index: 167811 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 1.7765. Min Range: -1.7765

Max Act: 0.9679. Min Act: -0.0000

Data Index: 905463 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 1.7765. Min Range: -1.7765

Max Act: 0.8824. Min Act: -0.0000

Data Index: 1059375 (C4 (Web Text))

Max Activating Token Index: 219