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

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

Neuron 1143 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: 1.3713. Min Range: -1.3713

Max Act: 1.3169. Min Act: -0.0000

Data Index: 1424264 (Python Code)

Max Activating Token Index: 725

Text #1

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.3713. Min Act: -0.0000

Data Index: 1357976 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.3215. Min Act: -0.0000

Data Index: 1567519 (Python Code)

Max Activating Token Index: 603

Text #3

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.2534. Min Act: -0.0000

Data Index: 575264 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.3162. Min Act: -0.0000

Data Index: 1453688 (Python Code)

Max Activating Token Index: 832

Text #5

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.3186. Min Act: -0.0000

Data Index: 1459537 (Python Code)

Max Activating Token Index: 752

Text #6

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.2967. Min Act: -0.0000

Data Index: 932130 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.2167. Min Act: -0.0000

Data Index: 659848 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.2005. Min Act: -0.0000

Data Index: 650263 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1988. Min Act: -0.0000

Data Index: 1184756 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1715. Min Act: -0.0000

Data Index: 800506 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1039. Min Act: -0.0000

Data Index: 1030731 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1609. Min Act: -0.0000

Data Index: 1475014 (Python Code)

Max Activating Token Index: 71

Text #13

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1598. Min Act: -0.0000

Data Index: 1484704 (Python Code)

Max Activating Token Index: 551

Text #14

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1516696 (Python Code)

Max Activating Token Index: 540

Text #15

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1346. Min Act: -0.0000

Data Index: 739800 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.0592. Min Act: -0.0000

Data Index: 1342868 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1266. Min Act: -0.0000

Data Index: 937421 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1214. Min Act: -0.0000

Data Index: 227604 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1114. Min Act: -0.0000

Data Index: 1079187 (C4 (Web Text))

Max Activating Token Index: 636