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

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

Neuron 4233 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8765. Min Range: -3.8765

Max Act: 3.8765. Min Act: -0.0000

Data Index: 1440216 (Python Code)

Max Activating Token Index: 387

Text #1

Max Range: 3.8765. Min Range: -3.8765

Max Act: 3.3579. Min Act: -0.0000

Data Index: 1565412 (Python Code)

Max Activating Token Index: 863

Text #2

Max Range: 3.8765. Min Range: -3.8765

Max Act: 3.4725. Min Act: -0.0000

Data Index: 1645877 (Python Code)

Max Activating Token Index: 861

Text #3

Max Range: 3.8765. Min Range: -3.8765

Max Act: 3.3050. Min Act: -0.0000

Data Index: 1561323 (Python Code)

Max Activating Token Index: 266

Text #4

Max Range: 3.8765. Min Range: -3.8765

Max Act: 3.4606. Min Act: -0.0000

Data Index: 1606973 (Python Code)

Max Activating Token Index: 122

Text #5

Max Range: 3.8765. Min Range: -3.8765

Max Act: 2.7317. Min Act: -0.0000

Data Index: 1500460 (Python Code)

Max Activating Token Index: 716

Text #6

Max Range: 3.8765. Min Range: -3.8765

Max Act: 2.6533. Min Act: -0.0000

Data Index: 1529421 (Python Code)

Max Activating Token Index: 124

Text #7

Max Range: 3.8765. Min Range: -3.8765

Max Act: 2.3694. Min Act: -0.0000

Data Index: 1611840 (Python Code)

Max Activating Token Index: 718

Text #8

Max Range: 3.8765. Min Range: -3.8765

Max Act: 2.5990. Min Act: -0.0000

Data Index: 1580904 (Python Code)

Max Activating Token Index: 211

Text #9

Max Range: 3.8765. Min Range: -3.8765

Max Act: 2.5633. Min Act: -0.0000

Data Index: 1437882 (Python Code)

Max Activating Token Index: 232

Text #10

Max Range: 3.8765. Min Range: -3.8765

Max Act: 2.5580. Min Act: -0.0000

Data Index: 1521521 (Python Code)

Max Activating Token Index: 236

Text #11

Max Range: 3.8765. Min Range: -3.8765

Max Act: 2.4388. Min Act: -0.0000

Data Index: 1529956 (Python Code)

Max Activating Token Index: 304

Text #12

Max Range: 3.8765. Min Range: -3.8765

Max Act: 2.2495. Min Act: -0.0000

Data Index: 1529065 (Python Code)

Max Activating Token Index: 444

Text #13

Max Range: 3.8765. Min Range: -3.8765

Max Act: 2.3604. Min Act: -0.0000

Data Index: 1381780 (Python Code)

Max Activating Token Index: 307

Text #14

Max Range: 3.8765. Min Range: -3.8765

Max Act: 2.2696. Min Act: -0.0000

Data Index: 1587418 (Python Code)

Max Activating Token Index: 716

Text #15

Max Range: 3.8765. Min Range: -3.8765

Max Act: 2.3714. Min Act: -0.0000

Data Index: 1399495 (Python Code)

Max Activating Token Index: 226

Text #16

Max Range: 3.8765. Min Range: -3.8765

Max Act: 2.5227. Min Act: -0.0000

Data Index: 1593868 (Python Code)

Max Activating Token Index: 294

Text #17

Max Range: 3.8765. Min Range: -3.8765

Max Act: 2.2368. Min Act: -0.0000

Data Index: 1625222 (Python Code)

Max Activating Token Index: 322

Text #18

Max Range: 3.8765. Min Range: -3.8765

Max Act: 2.3371. Min Act: -0.0000

Data Index: 1569021 (Python Code)

Max Activating Token Index: 263

Text #19

Max Range: 3.8765. Min Range: -3.8765

Max Act: 2.1066. Min Act: -0.0000

Data Index: 1375189 (Python Code)

Max Activating Token Index: 720