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

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

Neuron 3734 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0060. Min Act: -0.0003

Data Index: 979319 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0056. Min Act: -0.0003

Data Index: 95634 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0003

Data Index: 481782 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1482341 (Python Code)

Max Activating Token Index: 266

Text #4

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0057. Min Act: -0.0003

Data Index: 371305 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1600037 (Python Code)

Max Activating Token Index: 277

Text #6

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1507787 (Python Code)

Max Activating Token Index: 246

Text #7

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0003

Data Index: 770503 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0003

Data Index: 415405 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0051. Min Act: -0.0003

Data Index: 106057 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1052852 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0051. Min Act: -0.0003

Data Index: 763977 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1030683 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0049. Min Act: -0.0003

Data Index: 8909 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1427680 (Python Code)

Max Activating Token Index: 417

Text #15

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0053. Min Act: -0.0003

Data Index: 233194 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1413378 (Python Code)

Max Activating Token Index: 78

Text #17

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1131333 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1275288 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1120670 (C4 (Web Text))

Max Activating Token Index: 847