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

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

Neuron 4579 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: 1.7047. Min Range: -1.7047

Max Act: 1.7047. Min Act: -0.0000

Data Index: 1366766 (Python Code)

Max Activating Token Index: 408

Text #1

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.6598. Min Act: -0.0000

Data Index: 1489861 (Python Code)

Max Activating Token Index: 134

Text #2

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.6606. Min Act: -0.0000

Data Index: 1446539 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.6380. Min Act: -0.0000

Data Index: 1600757 (Python Code)

Max Activating Token Index: 423

Text #4

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.4067. Min Act: -0.0000

Data Index: 1630763 (Python Code)

Max Activating Token Index: 262

Text #5

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.3985. Min Act: -0.0000

Data Index: 1557636 (Python Code)

Max Activating Token Index: 188

Text #6

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.1907. Min Act: -0.0000

Data Index: 1575553 (Python Code)

Max Activating Token Index: 585

Text #7

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.2442. Min Act: -0.0000

Data Index: 1418579 (Python Code)

Max Activating Token Index: 24

Text #8

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.1655. Min Act: -0.0000

Data Index: 109782 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.1859. Min Act: -0.0000

Data Index: 383984 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.2110. Min Act: -0.0000

Data Index: 1417013 (Python Code)

Max Activating Token Index: 625

Text #11

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.2009. Min Act: -0.0000

Data Index: 3413 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.2073. Min Act: -0.0000

Data Index: 206895 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.1531. Min Act: -0.0000

Data Index: 771296 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.1863. Min Act: -0.0000

Data Index: 1463118 (Python Code)

Max Activating Token Index: 1004

Text #15

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.1663. Min Act: -0.0000

Data Index: 835593 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.1587. Min Act: -0.0000

Data Index: 423414 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1138473 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.1318. Min Act: -0.0000

Data Index: 804679 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.1247. Min Act: -0.0000

Data Index: 983991 (C4 (Web Text))

Max Activating Token Index: 600