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

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

Neuron 78 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: 0.0066. Min Range: -0.0066

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1297034 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0066. Min Act: -0.0006

Data Index: 525864 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0064. Min Act: -0.0006

Data Index: 523676 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0062. Min Act: -0.0006

Data Index: 627763 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0007

Data Index: 453001 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0061. Min Act: -0.0006

Data Index: 566686 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1406854 (Python Code)

Max Activating Token Index: 993

Text #7

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0057. Min Act: -0.0006

Data Index: 873358 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0006

Data Index: 406590 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0058. Min Act: -0.0006

Data Index: 101672 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0056. Min Act: -0.0006

Data Index: 526863 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0056. Min Act: -0.0006

Data Index: 483800 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0057. Min Act: -0.0006

Data Index: 150511 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1099307 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0057. Min Act: -0.0006

Data Index: 888365 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1204183 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0057. Min Act: -0.0005

Data Index: 904751 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0056. Min Act: -0.0005

Data Index: 346698 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0056. Min Act: -0.0006

Data Index: 385112 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0056. Min Act: -0.0006

Data Index: 75876 (C4 (Web Text))

Max Activating Token Index: 744