Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1357 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.9525. Min Act: -0.0001

Data Index: 581740 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 1.0605. Min Range: -1.0605

Max Act: 1.0605. Min Act: -0.0001

Data Index: 730545 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.9046. Min Act: -0.0001

Data Index: 1166142 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.9391. Min Act: -0.0001

Data Index: 843353 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.9353. Min Act: -0.0001

Data Index: 1098706 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.9363. Min Act: -0.0001

Data Index: 961048 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8834. Min Act: -0.0001

Data Index: 735646 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8640. Min Act: -0.0001

Data Index: 1156040 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8740. Min Act: -0.0001

Data Index: 986749 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8512. Min Act: -0.0001

Data Index: 1325716 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8418. Min Act: -0.0001

Data Index: 1079690 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8738. Min Act: -0.0001

Data Index: 1009540 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8183. Min Act: -0.0001

Data Index: 33204 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7900. Min Act: -0.0001

Data Index: 350556 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7851. Min Act: -0.0001

Data Index: 48453 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8670. Min Act: -0.0001

Data Index: 305376 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8099. Min Act: -0.0001

Data Index: 294662 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8612. Min Act: -0.0001

Data Index: 739819 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8223. Min Act: -0.0001

Data Index: 1090256 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7765. Min Act: -0.0001

Data Index: 519702 (C4 (Web Text))

Max Activating Token Index: 409