Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 635 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0097. Min Act: -0.0006

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0084. Min Act: -0.0005

Data Index: 1643779 (Python Code)

Max Activating Token Index: 700

Text #2

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0080. Min Act: -0.0005

Data Index: 1517451 (Python Code)

Max Activating Token Index: 943

Text #3

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0078. Min Act: -0.0005

Data Index: 1522753 (Python Code)

Max Activating Token Index: 243

Text #4

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0076. Min Act: -0.0005

Data Index: 1507671 (Python Code)

Max Activating Token Index: 124

Text #5

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0075. Min Act: -0.0005

Data Index: 1213837 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0071. Min Act: -0.0005

Data Index: 1637748 (Python Code)

Max Activating Token Index: 56

Text #7

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0068. Min Act: -0.0005

Data Index: 935352 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0065. Min Act: -0.0006

Data Index: 784054 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0066. Min Act: -0.0005

Data Index: 1580781 (Python Code)

Max Activating Token Index: 1012

Text #10

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0066. Min Act: -0.0005

Data Index: 1569939 (Python Code)

Max Activating Token Index: 850

Text #11

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1044588 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0065. Min Act: -0.0005

Data Index: 1503038 (Python Code)

Max Activating Token Index: 578

Text #13

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1520298 (Python Code)

Max Activating Token Index: 887

Text #14

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0064. Min Act: -0.0005

Data Index: 1439139 (Python Code)

Max Activating Token Index: 654

Text #15

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0062. Min Act: -0.0005

Data Index: 483708 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0061. Min Act: -0.0005

Data Index: 1582278 (Python Code)

Max Activating Token Index: 785

Text #17

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0060. Min Act: -0.0005

Data Index: 1534620 (Python Code)

Max Activating Token Index: 224

Text #18

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0060. Min Act: -0.0006

Data Index: 284481 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0060. Min Act: -0.0005

Data Index: 375857 (C4 (Web Text))

Max Activating Token Index: 867