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

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

Neuron 4352 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.8330. Min Act: -0.0000

Data Index: 1055317 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7201. Min Act: -0.0000

Data Index: 532515 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1015572 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6341. Min Act: -0.0000

Data Index: 831425 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6242. Min Act: -0.0000

Data Index: 927541 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5958. Min Act: -0.0000

Data Index: 988351 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5799. Min Act: -0.0000

Data Index: 590961 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1249118 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1157431 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5360. Min Act: -0.0000

Data Index: 348123 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5308. Min Act: -0.0000

Data Index: 639510 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1110694 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1215884 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.4879. Min Act: -0.0000

Data Index: 792906 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.4716. Min Act: -0.0000

Data Index: 991652 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.4659. Min Act: -0.0000

Data Index: 732199 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.4720. Min Act: -0.0000

Data Index: 247810 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.4420. Min Act: -0.0000

Data Index: 58852 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.4673. Min Act: -0.0000

Data Index: 782281 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.4627. Min Act: -0.0000

Data Index: 437912 (C4 (Web Text))

Max Activating Token Index: 750