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

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

Neuron 3948 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1779. Min Range: -4.1779

Max Act: 4.1779. Min Act: -0.0000

Data Index: 475186 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.7923. Min Act: -0.0000

Data Index: 1551852 (Python Code)

Max Activating Token Index: 183

Text #2

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.6923. Min Act: -0.0000

Data Index: 1604784 (Python Code)

Max Activating Token Index: 108

Text #3

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.5794. Min Act: -0.0000

Data Index: 772964 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.2508. Min Act: -0.0000

Data Index: 1564087 (Python Code)

Max Activating Token Index: 494

Text #5

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.1537. Min Act: -0.0000

Data Index: 1130295 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.1965. Min Act: -0.0000

Data Index: 116363 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.1855. Min Act: -0.0000

Data Index: 1393333 (Python Code)

Max Activating Token Index: 202

Text #8

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.3102. Min Act: -0.0000

Data Index: 1651616 (Python Code)

Max Activating Token Index: 591

Text #9

Max Range: 4.1779. Min Range: -4.1779

Max Act: 2.7739. Min Act: -0.0000

Data Index: 1512129 (Python Code)

Max Activating Token Index: 753

Text #10

Max Range: 4.1779. Min Range: -4.1779

Max Act: 2.7327. Min Act: -0.0000

Data Index: 1644585 (Python Code)

Max Activating Token Index: 577

Text #11

Max Range: 4.1779. Min Range: -4.1779

Max Act: 2.7709. Min Act: -0.0000

Data Index: 849231 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 4.1779. Min Range: -4.1779

Max Act: 2.5808. Min Act: -0.0000

Data Index: 275690 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 4.1779. Min Range: -4.1779

Max Act: 2.5298. Min Act: -0.0000

Data Index: 1479920 (Python Code)

Max Activating Token Index: 1004

Text #14

Max Range: 4.1779. Min Range: -4.1779

Max Act: 2.5008. Min Act: -0.0000

Data Index: 1600069 (Python Code)

Max Activating Token Index: 187

Text #15

Max Range: 4.1779. Min Range: -4.1779

Max Act: 2.4825. Min Act: -0.0000

Data Index: 1427281 (Python Code)

Max Activating Token Index: 782

Text #16

Max Range: 4.1779. Min Range: -4.1779

Max Act: 2.5899. Min Act: -0.0000

Data Index: 1178994 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 4.1779. Min Range: -4.1779

Max Act: 2.5702. Min Act: -0.0000

Data Index: 1603638 (Python Code)

Max Activating Token Index: 384

Text #18

Max Range: 4.1779. Min Range: -4.1779

Max Act: 2.7016. Min Act: -0.0000

Data Index: 1557708 (Python Code)

Max Activating Token Index: 251

Text #19

Max Range: 4.1779. Min Range: -4.1779

Max Act: 2.6482. Min Act: -0.0000

Data Index: 1385434 (Python Code)

Max Activating Token Index: 979