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

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

Neuron 1573 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0760. Min Act: -0.0001

Data Index: 474330 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0676. Min Act: -0.0001

Data Index: 974302 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1478626 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1545226 (Python Code)

Max Activating Token Index: 55

Text #4

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0634. Min Act: -0.0001

Data Index: 1523284 (Python Code)

Max Activating Token Index: 671

Text #5

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0603. Min Act: -0.0001

Data Index: 43123 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1413943 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1612150 (Python Code)

Max Activating Token Index: 697

Text #8

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0728. Min Act: -0.0001

Data Index: 1531116 (Python Code)

Max Activating Token Index: 711

Text #9

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0698. Min Act: -0.0001

Data Index: 1614932 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0689. Min Act: -0.0001

Data Index: 340645 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1253282 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1647986 (Python Code)

Max Activating Token Index: 237

Text #13

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0710. Min Act: -0.0001

Data Index: 67097 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1508800 (Python Code)

Max Activating Token Index: 802

Text #15

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1592998 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1429560 (Python Code)

Max Activating Token Index: 668

Text #17

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1389980 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0648. Min Act: -0.0001

Data Index: 1454339 (Python Code)

Max Activating Token Index: 966

Text #19

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0651. Min Act: -0.0001

Data Index: 104355 (C4 (Web Text))

Max Activating Token Index: 576