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

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

Neuron 3978 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: 0.5594. Min Range: -0.5594

Max Act: 0.5486. Min Act: -0.0000

Data Index: 178467 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.5594. Min Act: -0.0000

Data Index: 406576 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.5202. Min Act: -0.0000

Data Index: 866608 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.5238. Min Act: -0.0000

Data Index: 287989 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4937. Min Act: -0.0000

Data Index: 136067 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4885. Min Act: -0.0000

Data Index: 753363 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4729. Min Act: -0.0000

Data Index: 31237 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4463. Min Act: -0.0000

Data Index: 6021 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4513. Min Act: -0.0000

Data Index: 908845 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4695. Min Act: -0.0000

Data Index: 876799 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1279494 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1230780 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4706. Min Act: -0.0000

Data Index: 191430 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.3973. Min Act: -0.0000

Data Index: 551644 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4234. Min Act: -0.0000

Data Index: 929830 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4219. Min Act: -0.0000

Data Index: 155372 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4122. Min Act: -0.0000

Data Index: 248558 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1064910 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1260393 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4162. Min Act: -0.0000

Data Index: 546851 (C4 (Web Text))

Max Activating Token Index: 629