Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1407 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1909. Min Act: -0.0001

Data Index: 695228 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1996. Min Act: -0.0000

Data Index: 81942 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1876. Min Act: -0.0000

Data Index: 471848 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1888. Min Act: -0.0001

Data Index: 165131 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1596. Min Act: -0.0001

Data Index: 125702 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1633. Min Act: -0.0000

Data Index: 636997 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1777. Min Act: -0.0000

Data Index: 93535 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1634. Min Act: -0.0000

Data Index: 1159530 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1634. Min Act: -0.0001

Data Index: 1303153 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1686. Min Act: -0.0001

Data Index: 256281 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1692. Min Act: -0.0001

Data Index: 1012262 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1565. Min Act: -0.0001

Data Index: 502583 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1562. Min Act: -0.0001

Data Index: 1101551 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1556. Min Act: -0.0001

Data Index: 137109 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1429. Min Act: -0.0000

Data Index: 540661 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1527. Min Act: -0.0000

Data Index: 360126 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1352. Min Act: -0.0001

Data Index: 1226482 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1158801 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1499. Min Act: -0.0001

Data Index: 1414464 (Python Code)

Max Activating Token Index: 940

Text #19

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1447. Min Act: -0.0001

Data Index: 269228 (C4 (Web Text))

Max Activating Token Index: 307