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

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

Neuron 4508 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.3844. Min Act: -0.0000

Data Index: 1133876 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.3125. Min Act: -0.0000

Data Index: 1202048 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.1981. Min Act: -0.0000

Data Index: 660967 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 1.3844. Min Range: -1.3844

Max Act: 0.9959. Min Act: -0.0000

Data Index: 500385 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.0222. Min Act: -0.0000

Data Index: 1116153 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 1.3844. Min Range: -1.3844

Max Act: 0.9479. Min Act: -0.0000

Data Index: 346151 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.0974. Min Act: -0.0000

Data Index: 199038 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 1.3844. Min Range: -1.3844

Max Act: 0.9768. Min Act: -0.0000

Data Index: 126895 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 1.3844. Min Range: -1.3844

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1038360 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.0114. Min Act: -0.0000

Data Index: 799283 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 1.3844. Min Range: -1.3844

Max Act: 0.8502. Min Act: -0.0000

Data Index: 613675 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.0046. Min Act: -0.0000

Data Index: 53533 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 1.3844. Min Range: -1.3844

Max Act: 0.9982. Min Act: -0.0000

Data Index: 830122 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 1.3844. Min Range: -1.3844

Max Act: 0.8828. Min Act: -0.0000

Data Index: 908068 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 1.3844. Min Range: -1.3844

Max Act: 0.8603. Min Act: -0.0000

Data Index: 384830 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 1.3844. Min Range: -1.3844

Max Act: 0.8528. Min Act: -0.0000

Data Index: 918734 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 1.3844. Min Range: -1.3844

Max Act: 0.8952. Min Act: -0.0000

Data Index: 57773 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 1.3844. Min Range: -1.3844

Max Act: 0.9478. Min Act: -0.0000

Data Index: 40427 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 1.3844. Min Range: -1.3844

Max Act: 0.9414. Min Act: -0.0000

Data Index: 608647 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 1.3844. Min Range: -1.3844

Max Act: 0.8832. Min Act: -0.0000

Data Index: 381227 (C4 (Web Text))

Max Activating Token Index: 66