Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2353 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0022. Min Act: -0.0004

Data Index: 1467582 (Python Code)

Max Activating Token Index: 845

Text #1

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0017. Min Act: -0.0004

Data Index: 1640720 (Python Code)

Max Activating Token Index: 823

Text #2

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0016. Min Act: -0.0004

Data Index: 1376075 (Python Code)

Max Activating Token Index: 26

Text #3

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1505788 (Python Code)

Max Activating Token Index: 137

Text #4

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0016. Min Act: -0.0004

Data Index: 657976 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0015. Min Act: -0.0004

Data Index: 1399193 (Python Code)

Max Activating Token Index: 894

Text #6

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0015. Min Act: -0.0004

Data Index: 1616064 (Python Code)

Max Activating Token Index: 257

Text #7

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0015. Min Act: -0.0003

Data Index: 744542 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1397572 (Python Code)

Max Activating Token Index: 194

Text #9

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0015. Min Act: -0.0004

Data Index: 1082425 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0014. Min Act: -0.0004

Data Index: 856688 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0015. Min Act: -0.0004

Data Index: 1624348 (Python Code)

Max Activating Token Index: 912

Text #12

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0014. Min Act: -0.0004

Data Index: 239815 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0015. Min Act: -0.0004

Data Index: 381949 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1194538 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1417435 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0014. Min Act: -0.0004

Data Index: 1028751 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0014. Min Act: -0.0003

Data Index: 956825 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0015. Min Act: -0.0004

Data Index: 169479 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0014. Min Act: -0.0004

Data Index: 1406671 (Python Code)

Max Activating Token Index: 339