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

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

Neuron 565 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2281. Min Range: -4.2281

Max Act: 4.2281. Min Act: -0.0000

Data Index: 1360077 (Python Code)

Max Activating Token Index: 650

Text #1

Max Range: 4.2281. Min Range: -4.2281

Max Act: 4.0842. Min Act: -0.0000

Data Index: 1446739 (Python Code)

Max Activating Token Index: 57

Text #2

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.8567. Min Act: -0.0000

Data Index: 1498316 (Python Code)

Max Activating Token Index: 75

Text #3

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.8970. Min Act: -0.0000

Data Index: 1553180 (Python Code)

Max Activating Token Index: 148

Text #4

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.9014. Min Act: -0.0000

Data Index: 1553722 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.8752. Min Act: -0.0000

Data Index: 1552758 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 4.2281. Min Range: -4.2281

Max Act: 4.0007. Min Act: -0.0000

Data Index: 1517805 (Python Code)

Max Activating Token Index: 912

Text #7

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.5804. Min Act: -0.0000

Data Index: 1453937 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.5804. Min Act: -0.0000

Data Index: 1463463 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.8268. Min Act: -0.0000

Data Index: 1581316 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.3919. Min Act: -0.0000

Data Index: 1393583 (Python Code)

Max Activating Token Index: 623

Text #11

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.3203. Min Act: -0.0000

Data Index: 1403912 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.3685. Min Act: -0.0000

Data Index: 1633089 (Python Code)

Max Activating Token Index: 385

Text #13

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.3396. Min Act: -0.0000

Data Index: 1491237 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.3078. Min Act: -0.0000

Data Index: 1362500 (Python Code)

Max Activating Token Index: 348

Text #15

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.0857. Min Act: -0.0000

Data Index: 1621023 (Python Code)

Max Activating Token Index: 160

Text #16

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.0696. Min Act: -0.0000

Data Index: 1400424 (Python Code)

Max Activating Token Index: 611

Text #17

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.2025. Min Act: -0.0000

Data Index: 1554376 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.2012. Min Act: -0.0000

Data Index: 1611187 (Python Code)

Max Activating Token Index: 418

Text #19

Max Range: 4.2281. Min Range: -4.2281

Max Act: 3.0521. Min Act: -0.0000

Data Index: 1571281 (Python Code)

Max Activating Token Index: 508