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

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

Neuron 1814 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: 1.5946. Min Range: -1.5946

Max Act: 1.5946. Min Act: -0.0000

Data Index: 1531421 (Python Code)

Max Activating Token Index: 50

Text #1

Max Range: 1.5946. Min Range: -1.5946

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1498232 (Python Code)

Max Activating Token Index: 421

Text #2

Max Range: 1.5946. Min Range: -1.5946

Max Act: 1.0597. Min Act: 0.0000

Data Index: 1604020 (Python Code)

Max Activating Token Index: 333

Text #3

Max Range: 1.5946. Min Range: -1.5946

Max Act: 1.0338. Min Act: -0.0000

Data Index: 1385065 (Python Code)

Max Activating Token Index: 778

Text #4

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.9477. Min Act: -0.0000

Data Index: 1443024 (Python Code)

Max Activating Token Index: 729

Text #5

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.9393. Min Act: -0.0000

Data Index: 1450995 (Python Code)

Max Activating Token Index: 60

Text #6

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.9669. Min Act: -0.0000

Data Index: 1379752 (Python Code)

Max Activating Token Index: 698

Text #7

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.9578. Min Act: -0.0000

Data Index: 54294 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.9808. Min Act: 0.0000

Data Index: 1423739 (Python Code)

Max Activating Token Index: 975

Text #9

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.9526. Min Act: -0.0000

Data Index: 1494825 (Python Code)

Max Activating Token Index: 74

Text #10

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.9226. Min Act: -0.0000

Data Index: 1608888 (Python Code)

Max Activating Token Index: 670

Text #11

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1520963 (Python Code)

Max Activating Token Index: 816

Text #12

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.9192. Min Act: 0.0000

Data Index: 356205 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1108905 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1646503 (Python Code)

Max Activating Token Index: 558

Text #15

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1439106 (Python Code)

Max Activating Token Index: 344

Text #16

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1411784 (Python Code)

Max Activating Token Index: 698

Text #17

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.7439. Min Act: -0.0000

Data Index: 1405593 (Python Code)

Max Activating Token Index: 131

Text #18

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.7568. Min Act: 0.0000

Data Index: 647132 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 1.5946. Min Range: -1.5946

Max Act: 0.8025. Min Act: -0.0000

Data Index: 921868 (C4 (Web Text))

Max Activating Token Index: 177