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

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

Neuron 2353 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1738. Min Act: -0.0001

Data Index: 700543 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.0595. Min Act: -0.0001

Data Index: 666216 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.1239. Min Act: -0.0001

Data Index: 632093 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 1.1738. Min Range: -1.1738

Max Act: 1.0016. Min Act: -0.0001

Data Index: 1154638 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.9713. Min Act: -0.0001

Data Index: 835185 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.8702. Min Act: -0.0001

Data Index: 798411 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.9607. Min Act: -0.0001

Data Index: 106794 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.9577. Min Act: -0.0001

Data Index: 786978 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.9534. Min Act: -0.0001

Data Index: 822566 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.9117. Min Act: -0.0001

Data Index: 184495 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.8734. Min Act: -0.0001

Data Index: 1229906 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.8685. Min Act: -0.0001

Data Index: 1077555 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.8335. Min Act: -0.0001

Data Index: 98823 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.7675. Min Act: -0.0001

Data Index: 789557 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.8789. Min Act: -0.0001

Data Index: 953245 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.7798. Min Act: -0.0001

Data Index: 1220130 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.8422. Min Act: -0.0001

Data Index: 971956 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.8618. Min Act: -0.0001

Data Index: 1120587 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.7993. Min Act: -0.0001

Data Index: 300601 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 1.1738. Min Range: -1.1738

Max Act: 0.8466. Min Act: -0.0001

Data Index: 1333017 (C4 (Web Text))

Max Activating Token Index: 559