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

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

Neuron 1491 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: 0.1898. Min Range: -0.1898

Max Act: 0.1788. Min Act: -0.0000

Data Index: 546985 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1898. Min Act: -0.0001

Data Index: 1365457 (Python Code)

Max Activating Token Index: 891

Text #2

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1799. Min Act: -0.0000

Data Index: 338034 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1271575 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1580. Min Act: -0.0000

Data Index: 980575 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1619. Min Act: -0.0001

Data Index: 745297 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1678. Min Act: -0.0001

Data Index: 87894 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1613. Min Act: -0.0000

Data Index: 604706 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1603. Min Act: -0.0000

Data Index: 995914 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1565. Min Act: -0.0000

Data Index: 1188470 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1217402 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1494. Min Act: -0.0001

Data Index: 1400450 (Python Code)

Max Activating Token Index: 936

Text #12

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1480816 (Python Code)

Max Activating Token Index: 255

Text #13

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1509. Min Act: -0.0000

Data Index: 394332 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1505. Min Act: -0.0001

Data Index: 296901 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1483. Min Act: -0.0001

Data Index: 552794 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1518. Min Act: -0.0001

Data Index: 1154421 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1462. Min Act: -0.0000

Data Index: 541816 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1486. Min Act: -0.0000

Data Index: 694248 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1444. Min Act: -0.0001

Data Index: 1572426 (Python Code)

Max Activating Token Index: 320