Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1078 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1102. Min Act: -0.0002

Data Index: 1627711 (Python Code)

Max Activating Token Index: 115

Text #1

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1610222 (Python Code)

Max Activating Token Index: 342

Text #2

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1145. Min Act: -0.0002

Data Index: 1421390 (Python Code)

Max Activating Token Index: 838

Text #3

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1037. Min Act: -0.0002

Data Index: 1462586 (Python Code)

Max Activating Token Index: 512

Text #4

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1033. Min Act: 0.0002

Data Index: 1437152 (Python Code)

Max Activating Token Index: 708

Text #5

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1410695 (Python Code)

Max Activating Token Index: 78

Text #6

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1400946 (Python Code)

Max Activating Token Index: 157

Text #7

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1464623 (Python Code)

Max Activating Token Index: 658

Text #8

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1366632 (Python Code)

Max Activating Token Index: 746

Text #9

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1364470 (Python Code)

Max Activating Token Index: 132

Text #10

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1005. Min Act: -0.0002

Data Index: 1548581 (Python Code)

Max Activating Token Index: 916

Text #11

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1005. Min Act: -0.0002

Data Index: 1459591 (Python Code)

Max Activating Token Index: 768

Text #12

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1518388 (Python Code)

Max Activating Token Index: 683

Text #13

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1595137 (Python Code)

Max Activating Token Index: 802

Text #14

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0973. Min Act: -0.0001

Data Index: 1429981 (Python Code)

Max Activating Token Index: 77

Text #15

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1388096 (Python Code)

Max Activating Token Index: 834

Text #16

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1549065 (Python Code)

Max Activating Token Index: 333

Text #17

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0963. Min Act: -0.0001

Data Index: 1411034 (Python Code)

Max Activating Token Index: 880

Text #18

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1587172 (Python Code)

Max Activating Token Index: 264

Text #19

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0966. Min Act: 0.0001

Data Index: 1620539 (Python Code)

Max Activating Token Index: 232