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

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

Neuron 348 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: 1.5876. Min Range: -1.5876

Max Act: 1.5876. Min Act: -0.0000

Data Index: 1468147 (Python Code)

Max Activating Token Index: 1019

Text #1

Max Range: 1.5876. Min Range: -1.5876

Max Act: 1.3132. Min Act: -0.0000

Data Index: 1490415 (Python Code)

Max Activating Token Index: 821

Text #2

Max Range: 1.5876. Min Range: -1.5876

Max Act: 1.2312. Min Act: -0.0000

Data Index: 1562612 (Python Code)

Max Activating Token Index: 602

Text #3

Max Range: 1.5876. Min Range: -1.5876

Max Act: 1.2154. Min Act: -0.0000

Data Index: 1476292 (Python Code)

Max Activating Token Index: 951

Text #4

Max Range: 1.5876. Min Range: -1.5876

Max Act: 1.1277. Min Act: -0.0000

Data Index: 1570897 (Python Code)

Max Activating Token Index: 1006

Text #5

Max Range: 1.5876. Min Range: -1.5876

Max Act: 1.1866. Min Act: -0.0000

Data Index: 84990 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 1.5876. Min Range: -1.5876

Max Act: 1.1027. Min Act: -0.0000

Data Index: 1561248 (Python Code)

Max Activating Token Index: 631

Text #7

Max Range: 1.5876. Min Range: -1.5876

Max Act: 1.1904. Min Act: -0.0000

Data Index: 1376816 (Python Code)

Max Activating Token Index: 679

Text #8

Max Range: 1.5876. Min Range: -1.5876

Max Act: 1.0537. Min Act: -0.0000

Data Index: 1523587 (Python Code)

Max Activating Token Index: 341

Text #9

Max Range: 1.5876. Min Range: -1.5876

Max Act: 1.0196. Min Act: -0.0000

Data Index: 1466623 (Python Code)

Max Activating Token Index: 607

Text #10

Max Range: 1.5876. Min Range: -1.5876

Max Act: 1.0206. Min Act: -0.0000

Data Index: 1584756 (Python Code)

Max Activating Token Index: 253

Text #11

Max Range: 1.5876. Min Range: -1.5876

Max Act: 1.1190. Min Act: -0.0000

Data Index: 1606580 (Python Code)

Max Activating Token Index: 1015

Text #12

Max Range: 1.5876. Min Range: -1.5876

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1638035 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 1.5876. Min Range: -1.5876

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1538936 (Python Code)

Max Activating Token Index: 767

Text #14

Max Range: 1.5876. Min Range: -1.5876

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1618404 (Python Code)

Max Activating Token Index: 773

Text #15

Max Range: 1.5876. Min Range: -1.5876

Max Act: 1.0273. Min Act: -0.0000

Data Index: 1524249 (Python Code)

Max Activating Token Index: 338

Text #16

Max Range: 1.5876. Min Range: -1.5876

Max Act: 0.8941. Min Act: -0.0000

Data Index: 1627194 (Python Code)

Max Activating Token Index: 437

Text #17

Max Range: 1.5876. Min Range: -1.5876

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1585931 (Python Code)

Max Activating Token Index: 82

Text #18

Max Range: 1.5876. Min Range: -1.5876

Max Act: 0.8814. Min Act: -0.0000

Data Index: 1601317 (Python Code)

Max Activating Token Index: 1005

Text #19

Max Range: 1.5876. Min Range: -1.5876

Max Act: 0.9023. Min Act: -0.0000

Data Index: 840619 (C4 (Web Text))

Max Activating Token Index: 239