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

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

Neuron 520 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1824. Min Act: -0.0001

Data Index: 695967 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.2005. Min Act: -0.0001

Data Index: 578657 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1915. Min Act: -0.0001

Data Index: 205191 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1607740 (Python Code)

Max Activating Token Index: 507

Text #4

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1920. Min Act: -0.0001

Data Index: 202516 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1730. Min Act: -0.0001

Data Index: 694902 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1656. Min Act: -0.0001

Data Index: 1544200 (Python Code)

Max Activating Token Index: 230

Text #7

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1654. Min Act: -0.0001

Data Index: 1445802 (Python Code)

Max Activating Token Index: 63

Text #8

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1631. Min Act: -0.0001

Data Index: 562119 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1632. Min Act: -0.0001

Data Index: 736206 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1363. Min Act: -0.0001

Data Index: 1561659 (Python Code)

Max Activating Token Index: 76

Text #11

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1517. Min Act: -0.0001

Data Index: 1504330 (Python Code)

Max Activating Token Index: 469

Text #12

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1655. Min Act: -0.0001

Data Index: 926303 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1670. Min Act: -0.0001

Data Index: 174341 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1546. Min Act: -0.0001

Data Index: 986327 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1351. Min Act: -0.0001

Data Index: 55143 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1186810 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1666. Min Act: -0.0001

Data Index: 26640 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1580. Min Act: -0.0001

Data Index: 993895 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1551. Min Act: -0.0001

Data Index: 83310 (C4 (Web Text))

Max Activating Token Index: 906