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

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

Neuron 3582 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6948. Min Range: -4.6948

Max Act: 4.6210. Min Act: -0.0000

Data Index: 1434816 (Python Code)

Max Activating Token Index: 350

Text #1

Max Range: 4.6948. Min Range: -4.6948

Max Act: 4.6948. Min Act: -0.0000

Data Index: 1516152 (Python Code)

Max Activating Token Index: 933

Text #2

Max Range: 4.6948. Min Range: -4.6948

Max Act: 4.5079. Min Act: -0.0000

Data Index: 1439540 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 4.6948. Min Range: -4.6948

Max Act: 4.1015. Min Act: -0.0000

Data Index: 1642402 (Python Code)

Max Activating Token Index: 193

Text #4

Max Range: 4.6948. Min Range: -4.6948

Max Act: 4.4517. Min Act: -0.0000

Data Index: 1555732 (Python Code)

Max Activating Token Index: 503

Text #5

Max Range: 4.6948. Min Range: -4.6948

Max Act: 4.0714. Min Act: -0.0000

Data Index: 1418086 (Python Code)

Max Activating Token Index: 92

Text #6

Max Range: 4.6948. Min Range: -4.6948

Max Act: 3.8203. Min Act: -0.0000

Data Index: 1447964 (Python Code)

Max Activating Token Index: 227

Text #7

Max Range: 4.6948. Min Range: -4.6948

Max Act: 3.9925. Min Act: -0.0000

Data Index: 1466096 (Python Code)

Max Activating Token Index: 391

Text #8

Max Range: 4.6948. Min Range: -4.6948

Max Act: 3.8419. Min Act: -0.0000

Data Index: 1635783 (Python Code)

Max Activating Token Index: 161

Text #9

Max Range: 4.6948. Min Range: -4.6948

Max Act: 3.7856. Min Act: -0.0000

Data Index: 1522709 (Python Code)

Max Activating Token Index: 307

Text #10

Max Range: 4.6948. Min Range: -4.6948

Max Act: 3.6082. Min Act: -0.0000

Data Index: 1630882 (Python Code)

Max Activating Token Index: 678

Text #11

Max Range: 4.6948. Min Range: -4.6948

Max Act: 3.5909. Min Act: -0.0000

Data Index: 1401763 (Python Code)

Max Activating Token Index: 922

Text #12

Max Range: 4.6948. Min Range: -4.6948

Max Act: 3.3887. Min Act: -0.0000

Data Index: 1468073 (Python Code)

Max Activating Token Index: 228

Text #13

Max Range: 4.6948. Min Range: -4.6948

Max Act: 3.3556. Min Act: -0.0000

Data Index: 1653559 (Python Code)

Max Activating Token Index: 284

Text #14

Max Range: 4.6948. Min Range: -4.6948

Max Act: 3.5185. Min Act: -0.0000

Data Index: 1478816 (Python Code)

Max Activating Token Index: 622

Text #15

Max Range: 4.6948. Min Range: -4.6948

Max Act: 3.2033. Min Act: -0.0000

Data Index: 1451146 (Python Code)

Max Activating Token Index: 742

Text #16

Max Range: 4.6948. Min Range: -4.6948

Max Act: 3.1765. Min Act: -0.0000

Data Index: 1579910 (Python Code)

Max Activating Token Index: 999

Text #17

Max Range: 4.6948. Min Range: -4.6948

Max Act: 3.5101. Min Act: -0.0000

Data Index: 1610536 (Python Code)

Max Activating Token Index: 281

Text #18

Max Range: 4.6948. Min Range: -4.6948

Max Act: 3.4504. Min Act: -0.0000

Data Index: 1578041 (Python Code)

Max Activating Token Index: 915

Text #19

Max Range: 4.6948. Min Range: -4.6948

Max Act: 3.4574. Min Act: -0.0000

Data Index: 1377368 (Python Code)

Max Activating Token Index: 791