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

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

Neuron 2277 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1642872 (Python Code)

Max Activating Token Index: 687

Text #1

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0985. Min Act: -0.0002

Data Index: 1486585 (Python Code)

Max Activating Token Index: 156

Text #2

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1367286 (Python Code)

Max Activating Token Index: 270

Text #3

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1444458 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0973. Min Act: -0.0002

Data Index: 1550172 (Python Code)

Max Activating Token Index: 37

Text #5

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1391507 (Python Code)

Max Activating Token Index: 132

Text #6

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0949. Min Act: -0.0002

Data Index: 1652758 (Python Code)

Max Activating Token Index: 360

Text #7

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1511675 (Python Code)

Max Activating Token Index: 151

Text #8

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0922. Min Act: -0.0002

Data Index: 1455390 (Python Code)

Max Activating Token Index: 687

Text #9

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1507132 (Python Code)

Max Activating Token Index: 21

Text #10

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1608769 (Python Code)

Max Activating Token Index: 53

Text #11

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0905. Min Act: -0.0002

Data Index: 1627954 (Python Code)

Max Activating Token Index: 296

Text #12

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1486379 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0869. Min Act: -0.0002

Data Index: 1644119 (Python Code)

Max Activating Token Index: 492

Text #14

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0870. Min Act: -0.0002

Data Index: 1497732 (Python Code)

Max Activating Token Index: 634

Text #15

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0876. Min Act: -0.0002

Data Index: 1392175 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1406256 (Python Code)

Max Activating Token Index: 78

Text #17

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1471665 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1459438 (Python Code)

Max Activating Token Index: 144

Text #19

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0877. Min Act: -0.0002

Data Index: 1404964 (Python Code)

Max Activating Token Index: 382