Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1416 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0004

Data Index: 506552 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0004

Data Index: 1345257 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1648975 (Python Code)

Max Activating Token Index: 1016

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 1574314 (Python Code)

Max Activating Token Index: 1001

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 640654 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1513409 (Python Code)

Max Activating Token Index: 970

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0004

Data Index: 1298274 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0004

Data Index: 1585684 (Python Code)

Max Activating Token Index: 877

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1156669 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0004

Data Index: 117825 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0004

Data Index: 324856 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0003

Data Index: 68567 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1368603 (Python Code)

Max Activating Token Index: 934

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0004

Data Index: 1501600 (Python Code)

Max Activating Token Index: 841

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0004

Data Index: 129950 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0004

Data Index: 811746 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0004

Data Index: 524100 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0004

Data Index: 1143263 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0004

Data Index: 351263 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0004

Data Index: 393739 (C4 (Web Text))

Max Activating Token Index: 936