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

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

Neuron 4774 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1637. Min Range: -1.1637

Max Act: 1.1637. Min Act: 0.0000

Data Index: 1539027 (Python Code)

Max Activating Token Index: 959

Text #1

Max Range: 1.1637. Min Range: -1.1637

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1421367 (Python Code)

Max Activating Token Index: 739

Text #2

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.9319. Min Act: -0.0000

Data Index: 1519360 (Python Code)

Max Activating Token Index: 997

Text #3

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1383549 (Python Code)

Max Activating Token Index: 360

Text #4

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1419917 (Python Code)

Max Activating Token Index: 308

Text #5

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1533055 (Python Code)

Max Activating Token Index: 18

Text #6

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.7610. Min Act: -0.0000

Data Index: 638817 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.7813. Min Act: 0.0000

Data Index: 1517653 (Python Code)

Max Activating Token Index: 822

Text #8

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1162608 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.6668. Min Act: -0.0000

Data Index: 627905 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.6547. Min Act: -0.0000

Data Index: 1528676 (Python Code)

Max Activating Token Index: 813

Text #11

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.6074. Min Act: -0.0000

Data Index: 140286 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.6233. Min Act: 0.0000

Data Index: 1529922 (Python Code)

Max Activating Token Index: 344

Text #13

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1481561 (Python Code)

Max Activating Token Index: 310

Text #14

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.5716. Min Act: -0.0000

Data Index: 60112 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1536992 (Python Code)

Max Activating Token Index: 74

Text #16

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.5609. Min Act: -0.0000

Data Index: 1586100 (Python Code)

Max Activating Token Index: 1014

Text #17

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.5986. Min Act: 0.0000

Data Index: 1426248 (Python Code)

Max Activating Token Index: 268

Text #18

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.5491. Min Act: -0.0000

Data Index: 638610 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 1.1637. Min Range: -1.1637

Max Act: 0.5825. Min Act: -0.0000

Data Index: 452964 (C4 (Web Text))

Max Activating Token Index: 379