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

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

Neuron 986 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0337. Min Range: -1.0337

Max Act: 1.0337. Min Act: -0.0002

Data Index: 1516114 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9973. Min Act: -0.0002

Data Index: 1655538 (Python Code)

Max Activating Token Index: 2

Text #2

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9973. Min Act: -0.0002

Data Index: 1405439 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9973. Min Act: -0.0002

Data Index: 1425543 (Python Code)

Max Activating Token Index: 2

Text #4

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9973. Min Act: -0.0002

Data Index: 1368171 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9961. Min Act: -0.0002

Data Index: 1368556 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9986. Min Act: -0.0002

Data Index: 1598647 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9071. Min Act: -0.0002

Data Index: 1457383 (Python Code)

Max Activating Token Index: 2

Text #8

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9122. Min Act: -0.0002

Data Index: 1607145 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9282. Min Act: -0.0002

Data Index: 1478161 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9257. Min Act: -0.0002

Data Index: 1407032 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8309. Min Act: -0.0002

Data Index: 1473523 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8655. Min Act: -0.0002

Data Index: 1534397 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8655. Min Act: -0.0002

Data Index: 1617068 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8624. Min Act: -0.0002

Data Index: 1531967 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8100. Min Act: -0.0002

Data Index: 1552928 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8271. Min Act: -0.0002

Data Index: 1546824 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8271. Min Act: -0.0002

Data Index: 1588313 (Python Code)

Max Activating Token Index: 3

Text #18

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.7642. Min Act: -0.0002

Data Index: 1597204 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8092. Min Act: -0.0002

Data Index: 1503401 (Python Code)

Max Activating Token Index: 7