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

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

Neuron 3828 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: 4.6077. Min Range: -4.6077

Max Act: 4.6077. Min Act: -0.0000

Data Index: 1465563 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 4.6077. Min Range: -4.6077

Max Act: 3.7835. Min Act: -0.0000

Data Index: 1616091 (Python Code)

Max Activating Token Index: 883

Text #2

Max Range: 4.6077. Min Range: -4.6077

Max Act: 3.4975. Min Act: -0.0000

Data Index: 1572168 (Python Code)

Max Activating Token Index: 635

Text #3

Max Range: 4.6077. Min Range: -4.6077

Max Act: 3.6197. Min Act: -0.0000

Data Index: 1624844 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 4.6077. Min Range: -4.6077

Max Act: 3.4249. Min Act: -0.0000

Data Index: 1501462 (Python Code)

Max Activating Token Index: 36

Text #5

Max Range: 4.6077. Min Range: -4.6077

Max Act: 3.7025. Min Act: -0.0000

Data Index: 1653875 (Python Code)

Max Activating Token Index: 307

Text #6

Max Range: 4.6077. Min Range: -4.6077

Max Act: 3.5296. Min Act: -0.0000

Data Index: 1419180 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 4.6077. Min Range: -4.6077

Max Act: 3.6069. Min Act: -0.0000

Data Index: 1409787 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 4.6077. Min Range: -4.6077

Max Act: 3.2009. Min Act: -0.0000

Data Index: 1443425 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 4.6077. Min Range: -4.6077

Max Act: 3.2934. Min Act: -0.0000

Data Index: 1390081 (Python Code)

Max Activating Token Index: 152

Text #10

Max Range: 4.6077. Min Range: -4.6077

Max Act: 3.1326. Min Act: -0.0000

Data Index: 1636873 (Python Code)

Max Activating Token Index: 29

Text #11

Max Range: 4.6077. Min Range: -4.6077

Max Act: 3.1085. Min Act: -0.0000

Data Index: 1485913 (Python Code)

Max Activating Token Index: 449

Text #12

Max Range: 4.6077. Min Range: -4.6077

Max Act: 3.1281. Min Act: -0.0000

Data Index: 1649765 (Python Code)

Max Activating Token Index: 183

Text #13

Max Range: 4.6077. Min Range: -4.6077

Max Act: 3.1112. Min Act: -0.0000

Data Index: 1519255 (Python Code)

Max Activating Token Index: 596

Text #14

Max Range: 4.6077. Min Range: -4.6077

Max Act: 2.9612. Min Act: -0.0000

Data Index: 1445419 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 4.6077. Min Range: -4.6077

Max Act: 2.9698. Min Act: -0.0000

Data Index: 1574412 (Python Code)

Max Activating Token Index: 74

Text #16

Max Range: 4.6077. Min Range: -4.6077

Max Act: 2.8510. Min Act: -0.0000

Data Index: 1621507 (Python Code)

Max Activating Token Index: 785

Text #17

Max Range: 4.6077. Min Range: -4.6077

Max Act: 2.7433. Min Act: -0.0000

Data Index: 1423116 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 4.6077. Min Range: -4.6077

Max Act: 3.0304. Min Act: -0.0000

Data Index: 1468208 (Python Code)

Max Activating Token Index: 473

Text #19

Max Range: 4.6077. Min Range: -4.6077

Max Act: 2.7020. Min Act: -0.0000

Data Index: 1564237 (Python Code)

Max Activating Token Index: 64