Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1458 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1391865 (Python Code)

Max Activating Token Index: 962

Text #1

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1466351 (Python Code)

Max Activating Token Index: 965

Text #2

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1518067 (Python Code)

Max Activating Token Index: 991

Text #3

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0041. Min Act: -0.0003

Data Index: 1490056 (Python Code)

Max Activating Token Index: 890

Text #4

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0039. Min Act: -0.0003

Data Index: 1467627 (Python Code)

Max Activating Token Index: 1005

Text #5

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0042. Min Act: -0.0003

Data Index: 1652655 (Python Code)

Max Activating Token Index: 915

Text #6

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0041. Min Act: -0.0003

Data Index: 1471138 (Python Code)

Max Activating Token Index: 883

Text #7

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1482934 (Python Code)

Max Activating Token Index: 951

Text #8

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0040. Min Act: -0.0003

Data Index: 1418109 (Python Code)

Max Activating Token Index: 780

Text #9

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1451734 (Python Code)

Max Activating Token Index: 880

Text #10

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0038. Min Act: -0.0003

Data Index: 1417992 (Python Code)

Max Activating Token Index: 900

Text #11

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0038. Min Act: -0.0003

Data Index: 1490362 (Python Code)

Max Activating Token Index: 403

Text #12

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0038. Min Act: -0.0003

Data Index: 1621544 (Python Code)

Max Activating Token Index: 357

Text #13

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1489255 (Python Code)

Max Activating Token Index: 469

Text #14

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1609271 (Python Code)

Max Activating Token Index: 1006

Text #15

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1654209 (Python Code)

Max Activating Token Index: 896

Text #16

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1464656 (Python Code)

Max Activating Token Index: 1019

Text #17

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1436826 (Python Code)

Max Activating Token Index: 360

Text #18

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1540449 (Python Code)

Max Activating Token Index: 1018

Text #19

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1515707 (Python Code)

Max Activating Token Index: 779