Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1436 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0066. Min Act: -0.0005

Data Index: 213440 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0005

Data Index: 1059223 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0057. Min Act: -0.0005

Data Index: 367985 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0055. Min Act: -0.0005

Data Index: 262288 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1427613 (Python Code)

Max Activating Token Index: 689

Text #5

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0054. Min Act: -0.0005

Data Index: 1561564 (Python Code)

Max Activating Token Index: 981

Text #6

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1431378 (Python Code)

Max Activating Token Index: 707

Text #7

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1563632 (Python Code)

Max Activating Token Index: 690

Text #8

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1625892 (Python Code)

Max Activating Token Index: 509

Text #9

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0052. Min Act: -0.0005

Data Index: 1358099 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0053. Min Act: -0.0005

Data Index: 252791 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1475977 (Python Code)

Max Activating Token Index: 284

Text #12

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0053. Min Act: -0.0006

Data Index: 384804 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0053. Min Act: -0.0005

Data Index: 469820 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1452787 (Python Code)

Max Activating Token Index: 382

Text #15

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0052. Min Act: -0.0005

Data Index: 1174094 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1481623 (Python Code)

Max Activating Token Index: 959

Text #17

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0052. Min Act: -0.0005

Data Index: 620336 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0052. Min Act: -0.0005

Data Index: 1591002 (Python Code)

Max Activating Token Index: 958

Text #19

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0051. Min Act: -0.0006

Data Index: 902642 (C4 (Web Text))

Max Activating Token Index: 942