Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 83 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.3712. Min Range: -4.3712

Max Act: 4.3712. Min Act: -0.0000

Data Index: 1540933 (Python Code)

Max Activating Token Index: 713

Text #1

Max Range: 4.3712. Min Range: -4.3712

Max Act: 4.0083. Min Act: -0.0000

Data Index: 1366031 (Python Code)

Max Activating Token Index: 560

Text #2

Max Range: 4.3712. Min Range: -4.3712

Max Act: 3.6065. Min Act: -0.0001

Data Index: 1463127 (Python Code)

Max Activating Token Index: 679

Text #3

Max Range: 4.3712. Min Range: -4.3712

Max Act: 3.5588. Min Act: -0.0000

Data Index: 1460874 (Python Code)

Max Activating Token Index: 928

Text #4

Max Range: 4.3712. Min Range: -4.3712

Max Act: 4.0738. Min Act: -0.0000

Data Index: 1405794 (Python Code)

Max Activating Token Index: 994

Text #5

Max Range: 4.3712. Min Range: -4.3712

Max Act: 3.8231. Min Act: -0.0000

Data Index: 1567869 (Python Code)

Max Activating Token Index: 687

Text #6

Max Range: 4.3712. Min Range: -4.3712

Max Act: 3.9502. Min Act: -0.0000

Data Index: 1639588 (Python Code)

Max Activating Token Index: 594

Text #7

Max Range: 4.3712. Min Range: -4.3712

Max Act: 3.5790. Min Act: -0.0000

Data Index: 1551413 (Python Code)

Max Activating Token Index: 65

Text #8

Max Range: 4.3712. Min Range: -4.3712

Max Act: 3.2631. Min Act: -0.0000

Data Index: 1416399 (Python Code)

Max Activating Token Index: 293

Text #9

Max Range: 4.3712. Min Range: -4.3712

Max Act: 3.4975. Min Act: -0.0000

Data Index: 1470174 (Python Code)

Max Activating Token Index: 634

Text #10

Max Range: 4.3712. Min Range: -4.3712

Max Act: 3.2694. Min Act: -0.0000

Data Index: 1459063 (Python Code)

Max Activating Token Index: 509

Text #11

Max Range: 4.3712. Min Range: -4.3712

Max Act: 3.2500. Min Act: -0.0000

Data Index: 1376664 (Python Code)

Max Activating Token Index: 430

Text #12

Max Range: 4.3712. Min Range: -4.3712

Max Act: 3.3690. Min Act: -0.0000

Data Index: 1564764 (Python Code)

Max Activating Token Index: 175

Text #13

Max Range: 4.3712. Min Range: -4.3712

Max Act: 3.0208. Min Act: -0.0000

Data Index: 1510400 (Python Code)

Max Activating Token Index: 573

Text #14

Max Range: 4.3712. Min Range: -4.3712

Max Act: 3.1182. Min Act: -0.0000

Data Index: 1543273 (Python Code)

Max Activating Token Index: 7

Text #15

Max Range: 4.3712. Min Range: -4.3712

Max Act: 3.1020. Min Act: -0.0000

Data Index: 1376984 (Python Code)

Max Activating Token Index: 49

Text #16

Max Range: 4.3712. Min Range: -4.3712

Max Act: 2.9351. Min Act: -0.0000

Data Index: 1450231 (Python Code)

Max Activating Token Index: 281

Text #17

Max Range: 4.3712. Min Range: -4.3712

Max Act: 2.9191. Min Act: -0.0000

Data Index: 1557366 (Python Code)

Max Activating Token Index: 415

Text #18

Max Range: 4.3712. Min Range: -4.3712

Max Act: 3.2030. Min Act: -0.0000

Data Index: 1545722 (Python Code)

Max Activating Token Index: 451

Text #19

Max Range: 4.3712. Min Range: -4.3712

Max Act: 3.0172. Min Act: -0.0000

Data Index: 1626227 (Python Code)

Max Activating Token Index: 514