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

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

Neuron 2093 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: 3.3976. Min Range: -3.3976

Max Act: 3.3976. Min Act: -0.0000

Data Index: 1650965 (Python Code)

Max Activating Token Index: 290

Text #1

Max Range: 3.3976. Min Range: -3.3976

Max Act: 3.0403. Min Act: -0.0000

Data Index: 1460921 (Python Code)

Max Activating Token Index: 443

Text #2

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.8966. Min Act: -0.0000

Data Index: 1410854 (Python Code)

Max Activating Token Index: 50

Text #3

Max Range: 3.3976. Min Range: -3.3976

Max Act: 3.0077. Min Act: -0.0000

Data Index: 1601453 (Python Code)

Max Activating Token Index: 982

Text #4

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.9935. Min Act: -0.0000

Data Index: 1286085 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.6370. Min Act: -0.0000

Data Index: 1578894 (Python Code)

Max Activating Token Index: 684

Text #6

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.5095. Min Act: -0.0000

Data Index: 1555265 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.3840. Min Act: -0.0000

Data Index: 108908 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.5789. Min Act: -0.0000

Data Index: 1252005 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.2308. Min Act: -0.0000

Data Index: 1500056 (Python Code)

Max Activating Token Index: 472

Text #10

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.3405. Min Act: -0.0000

Data Index: 1183285 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.1497. Min Act: -0.0000

Data Index: 1045608 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.1054. Min Act: -0.0000

Data Index: 1483059 (Python Code)

Max Activating Token Index: 198

Text #13

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.3339. Min Act: -0.0000

Data Index: 199038 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.2100. Min Act: -0.0000

Data Index: 1131481 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.2119. Min Act: -0.0000

Data Index: 1388513 (Python Code)

Max Activating Token Index: 102

Text #16

Max Range: 3.3976. Min Range: -3.3976

Max Act: 1.9872. Min Act: -0.0000

Data Index: 1585874 (Python Code)

Max Activating Token Index: 295

Text #17

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.1959. Min Act: -0.0000

Data Index: 1597279 (Python Code)

Max Activating Token Index: 31

Text #18

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.0613. Min Act: -0.0000

Data Index: 1531096 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 3.3976. Min Range: -3.3976

Max Act: 2.1725. Min Act: -0.0000

Data Index: 1476568 (Python Code)

Max Activating Token Index: 41