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

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

Neuron 172 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1277. Min Range: -1.1277

Max Act: 1.1277. Min Act: -0.0000

Data Index: 1489078 (Python Code)

Max Activating Token Index: 111

Text #1

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1416355 (Python Code)

Max Activating Token Index: 120

Text #2

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.9205. Min Act: -0.0000

Data Index: 956076 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 1.1277. Min Range: -1.1277

Max Act: 1.0602. Min Act: -0.0000

Data Index: 318108 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.9621. Min Act: -0.0000

Data Index: 606679 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.8885. Min Act: -0.0000

Data Index: 26062 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1451544 (Python Code)

Max Activating Token Index: 997

Text #7

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1240102 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1018727 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.8953. Min Act: -0.0000

Data Index: 1519463 (Python Code)

Max Activating Token Index: 104

Text #10

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1641356 (Python Code)

Max Activating Token Index: 92

Text #11

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1507286 (Python Code)

Max Activating Token Index: 90

Text #12

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1581381 (Python Code)

Max Activating Token Index: 83

Text #13

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1574738 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.7189. Min Act: -0.0000

Data Index: 920062 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.8408. Min Act: -0.0000

Data Index: 878177 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1403456 (Python Code)

Max Activating Token Index: 79

Text #17

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1636065 (Python Code)

Max Activating Token Index: 82

Text #18

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.7819. Min Act: -0.0000

Data Index: 92327 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 1.1277. Min Range: -1.1277

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1478890 (Python Code)

Max Activating Token Index: 134