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

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

Neuron 1707 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: 0.0078. Min Range: -0.0078

Max Act: 0.0078. Min Act: -0.0003

Data Index: 716390 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0074. Min Act: -0.0003

Data Index: 869321 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0068. Min Act: -0.0003

Data Index: 396957 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0071. Min Act: -0.0002

Data Index: 1612847 (Python Code)

Max Activating Token Index: 20

Text #4

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0071. Min Act: -0.0003

Data Index: 150503 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0067. Min Act: -0.0003

Data Index: 534789 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1122494 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0067. Min Act: -0.0002

Data Index: 967754 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1403079 (Python Code)

Max Activating Token Index: 846

Text #9

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0067. Min Act: -0.0003

Data Index: 941720 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1463962 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0066. Min Act: -0.0003

Data Index: 550235 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0065. Min Act: -0.0002

Data Index: 1246053 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0067. Min Act: -0.0003

Data Index: 600897 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0064. Min Act: -0.0002

Data Index: 603189 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1041222 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0066. Min Act: -0.0003

Data Index: 352067 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1640716 (Python Code)

Max Activating Token Index: 45

Text #18

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1389605 (Python Code)

Max Activating Token Index: 1000

Text #19

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0063. Min Act: -0.0002

Data Index: 765913 (C4 (Web Text))

Max Activating Token Index: 35