Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1987 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1149. Min Act: -0.0002

Data Index: 1573738 (Python Code)

Max Activating Token Index: 394

Text #1

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1062. Min Act: -0.0002

Data Index: 1439956 (Python Code)

Max Activating Token Index: 418

Text #2

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1043. Min Act: -0.0002

Data Index: 1370982 (Python Code)

Max Activating Token Index: 45

Text #3

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1611592 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1026. Min Act: -0.0002

Data Index: 1375377 (Python Code)

Max Activating Token Index: 762

Text #5

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0999. Min Act: -0.0002

Data Index: 1388774 (Python Code)

Max Activating Token Index: 453

Text #6

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0970. Min Act: -0.0002

Data Index: 1473901 (Python Code)

Max Activating Token Index: 150

Text #7

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1022. Min Act: -0.0002

Data Index: 1627200 (Python Code)

Max Activating Token Index: 195

Text #8

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1528915 (Python Code)

Max Activating Token Index: 213

Text #9

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0999. Min Act: -0.0002

Data Index: 1649233 (Python Code)

Max Activating Token Index: 732

Text #10

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0945. Min Act: -0.0002

Data Index: 1573764 (Python Code)

Max Activating Token Index: 847

Text #11

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1425977 (Python Code)

Max Activating Token Index: 548

Text #12

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1426897 (Python Code)

Max Activating Token Index: 252

Text #13

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1483818 (Python Code)

Max Activating Token Index: 504

Text #14

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1027. Min Act: -0.0002

Data Index: 1447722 (Python Code)

Max Activating Token Index: 84

Text #15

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1451249 (Python Code)

Max Activating Token Index: 924

Text #16

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1034. Min Act: -0.0002

Data Index: 1467055 (Python Code)

Max Activating Token Index: 829

Text #17

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1449671 (Python Code)

Max Activating Token Index: 619

Text #18

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0935. Min Act: -0.0002

Data Index: 1544333 (Python Code)

Max Activating Token Index: 453

Text #19

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1590087 (Python Code)

Max Activating Token Index: 906