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

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

Neuron 4557 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1296929 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1645604 (Python Code)

Max Activating Token Index: 240

Text #2

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1542358 (Python Code)

Max Activating Token Index: 682

Text #3

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1464849 (Python Code)

Max Activating Token Index: 749

Text #4

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0002

Data Index: 995630 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0002

Data Index: 622215 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1454808 (Python Code)

Max Activating Token Index: 836

Text #7

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1495646 (Python Code)

Max Activating Token Index: 846

Text #8

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0059. Min Act: -0.0002

Data Index: 524007 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0059. Min Act: -0.0002

Data Index: 898061 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1486605 (Python Code)

Max Activating Token Index: 615

Text #11

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0059. Min Act: -0.0002

Data Index: 987607 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0058. Min Act: -0.0002

Data Index: 87899 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1560537 (Python Code)

Max Activating Token Index: 70

Text #14

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1238474 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0002

Data Index: 411341 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1028381 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1271411 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0058. Min Act: -0.0002

Data Index: 288667 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0002

Data Index: 84297 (C4 (Web Text))

Max Activating Token Index: 7