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

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

Neuron 4624 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: 2.5354. Min Range: -2.5354

Max Act: 2.5354. Min Act: -0.0000

Data Index: 1337492 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 2.5354. Min Range: -2.5354

Max Act: 2.3632. Min Act: -0.0000

Data Index: 657657 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 2.5354. Min Range: -2.5354

Max Act: 2.4080. Min Act: -0.0000

Data Index: 1002449 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.6285. Min Act: -0.0000

Data Index: 1637054 (Python Code)

Max Activating Token Index: 631

Text #4

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.8103. Min Act: -0.0000

Data Index: 1443549 (Python Code)

Max Activating Token Index: 40

Text #5

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.6132. Min Act: -0.0000

Data Index: 1618776 (Python Code)

Max Activating Token Index: 97

Text #6

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.6192. Min Act: -0.0000

Data Index: 483890 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.6180. Min Act: -0.0000

Data Index: 1486425 (Python Code)

Max Activating Token Index: 41

Text #8

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.5441. Min Act: -0.0000

Data Index: 1514025 (Python Code)

Max Activating Token Index: 534

Text #9

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.5379. Min Act: -0.0000

Data Index: 1533592 (Python Code)

Max Activating Token Index: 333

Text #10

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.5431. Min Act: -0.0000

Data Index: 1471775 (Python Code)

Max Activating Token Index: 51

Text #11

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.5860. Min Act: -0.0000

Data Index: 1419853 (Python Code)

Max Activating Token Index: 777

Text #12

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.5231. Min Act: -0.0000

Data Index: 1455345 (Python Code)

Max Activating Token Index: 346

Text #13

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.5523. Min Act: -0.0000

Data Index: 1598663 (Python Code)

Max Activating Token Index: 792

Text #14

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.6869. Min Act: -0.0000

Data Index: 1440695 (Python Code)

Max Activating Token Index: 70

Text #15

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.4370. Min Act: -0.0000

Data Index: 1527264 (Python Code)

Max Activating Token Index: 19

Text #16

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.5200. Min Act: -0.0000

Data Index: 1516025 (Python Code)

Max Activating Token Index: 596

Text #17

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.5211. Min Act: -0.0000

Data Index: 1472410 (Python Code)

Max Activating Token Index: 940

Text #18

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.5855. Min Act: -0.0000

Data Index: 672454 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 2.5354. Min Range: -2.5354

Max Act: 1.4639. Min Act: -0.0000

Data Index: 1645370 (Python Code)

Max Activating Token Index: 526