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

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

Neuron 4916 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1734. Min Range: -3.1734

Max Act: 3.1734. Min Act: -0.0000

Data Index: 1437851 (Python Code)

Max Activating Token Index: 1021

Text #1

Max Range: 3.1734. Min Range: -3.1734

Max Act: 2.9480. Min Act: -0.0000

Data Index: 1386664 (Python Code)

Max Activating Token Index: 506

Text #2

Max Range: 3.1734. Min Range: -3.1734

Max Act: 2.5764. Min Act: -0.0000

Data Index: 1557964 (Python Code)

Max Activating Token Index: 65

Text #3

Max Range: 3.1734. Min Range: -3.1734

Max Act: 2.3815. Min Act: -0.0000

Data Index: 1642498 (Python Code)

Max Activating Token Index: 788

Text #4

Max Range: 3.1734. Min Range: -3.1734

Max Act: 2.3259. Min Act: -0.0000

Data Index: 1439537 (Python Code)

Max Activating Token Index: 799

Text #5

Max Range: 3.1734. Min Range: -3.1734

Max Act: 2.0606. Min Act: -0.0000

Data Index: 1656828 (Python Code)

Max Activating Token Index: 403

Text #6

Max Range: 3.1734. Min Range: -3.1734

Max Act: 2.0148. Min Act: -0.0000

Data Index: 1376413 (Python Code)

Max Activating Token Index: 980

Text #7

Max Range: 3.1734. Min Range: -3.1734

Max Act: 1.9294. Min Act: -0.0000

Data Index: 425853 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 3.1734. Min Range: -3.1734

Max Act: 1.8588. Min Act: -0.0000

Data Index: 1489551 (Python Code)

Max Activating Token Index: 449

Text #9

Max Range: 3.1734. Min Range: -3.1734

Max Act: 1.9944. Min Act: -0.0000

Data Index: 1623936 (Python Code)

Max Activating Token Index: 839

Text #10

Max Range: 3.1734. Min Range: -3.1734

Max Act: 1.8360. Min Act: -0.0000

Data Index: 1396503 (Python Code)

Max Activating Token Index: 444

Text #11

Max Range: 3.1734. Min Range: -3.1734

Max Act: 1.8270. Min Act: -0.0000

Data Index: 1378769 (Python Code)

Max Activating Token Index: 807

Text #12

Max Range: 3.1734. Min Range: -3.1734

Max Act: 1.8193. Min Act: -0.0000

Data Index: 1508806 (Python Code)

Max Activating Token Index: 715

Text #13

Max Range: 3.1734. Min Range: -3.1734

Max Act: 1.8156. Min Act: -0.0000

Data Index: 1402128 (Python Code)

Max Activating Token Index: 188

Text #14

Max Range: 3.1734. Min Range: -3.1734

Max Act: 1.7844. Min Act: -0.0000

Data Index: 1493212 (Python Code)

Max Activating Token Index: 748

Text #15

Max Range: 3.1734. Min Range: -3.1734

Max Act: 1.7198. Min Act: -0.0000

Data Index: 1545372 (Python Code)

Max Activating Token Index: 778

Text #16

Max Range: 3.1734. Min Range: -3.1734

Max Act: 1.7335. Min Act: -0.0000

Data Index: 1367123 (Python Code)

Max Activating Token Index: 354

Text #17

Max Range: 3.1734. Min Range: -3.1734

Max Act: 1.6806. Min Act: -0.0000

Data Index: 1591117 (Python Code)

Max Activating Token Index: 723

Text #18

Max Range: 3.1734. Min Range: -3.1734

Max Act: 1.7850. Min Act: -0.0000

Data Index: 1479556 (Python Code)

Max Activating Token Index: 281

Text #19

Max Range: 3.1734. Min Range: -3.1734

Max Act: 1.5919. Min Act: -0.0000

Data Index: 1585678 (Python Code)

Max Activating Token Index: 430