Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 640 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1500658 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1374657 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1559616 (Python Code)

Max Activating Token Index: 852

Text #3

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1470523 (Python Code)

Max Activating Token Index: 775

Text #4

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1065862 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1444959 (Python Code)

Max Activating Token Index: 930

Text #6

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1549697 (Python Code)

Max Activating Token Index: 749

Text #7

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1393686 (Python Code)

Max Activating Token Index: 47

Text #8

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1638747 (Python Code)

Max Activating Token Index: 577

Text #9

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1621706 (Python Code)

Max Activating Token Index: 718

Text #10

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1438233 (Python Code)

Max Activating Token Index: 608

Text #11

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1560202 (Python Code)

Max Activating Token Index: 530

Text #12

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1470477 (Python Code)

Max Activating Token Index: 427

Text #13

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1599281 (Python Code)

Max Activating Token Index: 379

Text #14

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1364861 (Python Code)

Max Activating Token Index: 825

Text #15

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1510183 (Python Code)

Max Activating Token Index: 785

Text #16

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1446663 (Python Code)

Max Activating Token Index: 393

Text #17

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1418233 (Python Code)

Max Activating Token Index: 434

Text #18

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1364273 (Python Code)

Max Activating Token Index: 634

Text #19

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1450669 (Python Code)

Max Activating Token Index: 116