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

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

Neuron 910 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1276. Min Range: -2.1276

Max Act: 2.1276. Min Act: -0.0000

Data Index: 949792 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.9807. Min Act: -0.0000

Data Index: 456263 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.8803. Min Act: -0.0000

Data Index: 872019 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.6707. Min Act: -0.0000

Data Index: 523724 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.6914. Min Act: -0.0000

Data Index: 669182 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.6225. Min Act: -0.0000

Data Index: 1070944 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1486051 (Python Code)

Max Activating Token Index: 539

Text #7

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.4576. Min Act: -0.0000

Data Index: 448510 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.4489. Min Act: -0.0000

Data Index: 1402955 (Python Code)

Max Activating Token Index: 822

Text #9

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.4382. Min Act: -0.0000

Data Index: 1246623 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.4306. Min Act: -0.0000

Data Index: 1165741 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.4116. Min Act: -0.0000

Data Index: 1272386 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.5032. Min Act: -0.0000

Data Index: 1395058 (Python Code)

Max Activating Token Index: 651

Text #13

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.3816. Min Act: -0.0000

Data Index: 1598416 (Python Code)

Max Activating Token Index: 333

Text #14

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.3881. Min Act: -0.0000

Data Index: 502972 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.3848. Min Act: -0.0000

Data Index: 35964 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.4683. Min Act: -0.0000

Data Index: 811137 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.3661. Min Act: -0.0000

Data Index: 350867 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.3787. Min Act: -0.0000

Data Index: 494997 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 2.1276. Min Range: -2.1276

Max Act: 1.3667. Min Act: -0.0000

Data Index: 298351 (C4 (Web Text))

Max Activating Token Index: 583