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

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

Neuron 5159 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: 0.7984. Min Range: -0.7984

Max Act: 0.7076. Min Act: -0.0000

Data Index: 316160 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7984. Min Act: -0.0000

Data Index: 221521 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1214669 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7079. Min Act: -0.0000

Data Index: 85098 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1274878 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7104. Min Act: -0.0000

Data Index: 562908 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1497232 (Python Code)

Max Activating Token Index: 749

Text #7

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7266. Min Act: -0.0000

Data Index: 673963 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1556187 (Python Code)

Max Activating Token Index: 662

Text #9

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1432910 (Python Code)

Max Activating Token Index: 666

Text #10

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1054911 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6208. Min Act: -0.0000

Data Index: 190050 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1455133 (Python Code)

Max Activating Token Index: 150

Text #13

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1468399 (Python Code)

Max Activating Token Index: 914

Text #14

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1431141 (Python Code)

Max Activating Token Index: 909

Text #15

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1457675 (Python Code)

Max Activating Token Index: 800

Text #16

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1551798 (Python Code)

Max Activating Token Index: 779

Text #17

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1640446 (Python Code)

Max Activating Token Index: 682

Text #18

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1450589 (Python Code)

Max Activating Token Index: 598

Text #19

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5583. Min Act: -0.0000

Data Index: 772202 (C4 (Web Text))

Max Activating Token Index: 177