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

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

Neuron 3484 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2521. Min Act: -0.0000

Data Index: 484423 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1464872 (Python Code)

Max Activating Token Index: 117

Text #2

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1281. Min Act: -0.0000

Data Index: 1398230 (Python Code)

Max Activating Token Index: 279

Text #3

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1182. Min Act: -0.0000

Data Index: 1538606 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1582199 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1398722 (Python Code)

Max Activating Token Index: 322

Text #6

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1424633 (Python Code)

Max Activating Token Index: 980

Text #7

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1571894 (Python Code)

Max Activating Token Index: 119

Text #8

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1143. Min Act: -0.0000

Data Index: 1490985 (Python Code)

Max Activating Token Index: 186

Text #9

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1386938 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1531296 (Python Code)

Max Activating Token Index: 464

Text #11

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1520823 (Python Code)

Max Activating Token Index: 732

Text #12

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1571104 (Python Code)

Max Activating Token Index: 54

Text #13

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1651042 (Python Code)

Max Activating Token Index: 176

Text #14

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1429414 (Python Code)

Max Activating Token Index: 890

Text #15

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1050. Min Act: -0.0000

Data Index: 1560627 (Python Code)

Max Activating Token Index: 227

Text #16

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1529430 (Python Code)

Max Activating Token Index: 983

Text #17

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1362729 (Python Code)

Max Activating Token Index: 172

Text #18

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1625068 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1560626 (Python Code)

Max Activating Token Index: 441