Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4012 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.9574. Min Act: 0.0000

Data Index: 1431196 (Python Code)

Max Activating Token Index: 96

Text #1

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1440614 (Python Code)

Max Activating Token Index: 189

Text #2

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1620679 (Python Code)

Max Activating Token Index: 974

Text #3

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.7452. Min Act: -0.0000

Data Index: 1166488 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1638781 (Python Code)

Max Activating Token Index: 401

Text #5

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.7109. Min Act: 0.0000

Data Index: 1504370 (Python Code)

Max Activating Token Index: 355

Text #6

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.6886. Min Act: 0.0001

Data Index: 1497651 (Python Code)

Max Activating Token Index: 264

Text #7

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.6944. Min Act: 0.0000

Data Index: 1457899 (Python Code)

Max Activating Token Index: 114

Text #8

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1250111 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.6194. Min Act: -0.0000

Data Index: 826324 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1598617 (Python Code)

Max Activating Token Index: 351

Text #11

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1225776 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.5908. Min Act: 0.0001

Data Index: 1444647 (Python Code)

Max Activating Token Index: 881

Text #13

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1520403 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1443663 (Python Code)

Max Activating Token Index: 453

Text #15

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1505341 (Python Code)

Max Activating Token Index: 808

Text #16

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1060850 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.6036. Min Act: 0.0000

Data Index: 1639439 (Python Code)

Max Activating Token Index: 1020

Text #18

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.6070. Min Act: -0.0000

Data Index: 572743 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.9574. Min Range: -0.9574

Max Act: 0.5634. Min Act: 0.0000

Data Index: 1649874 (Python Code)

Max Activating Token Index: 813