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

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

Neuron 2567 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.2059. Min Act: -0.0000

Data Index: 934178 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1414210 (Python Code)

Max Activating Token Index: 747

Text #2

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1184236 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1293458 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1678. Min Act: -0.0000

Data Index: 426855 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1606. Min Act: -0.0000

Data Index: 351734 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1345128 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1474325 (Python Code)

Max Activating Token Index: 758

Text #8

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1516. Min Act: -0.0000

Data Index: 420150 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1571586 (Python Code)

Max Activating Token Index: 725

Text #10

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1524806 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1344. Min Act: -0.0000

Data Index: 613660 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1409652 (Python Code)

Max Activating Token Index: 467

Text #13

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1440. Min Act: -0.0000

Data Index: 33302 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1441. Min Act: -0.0000

Data Index: 823349 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1422838 (Python Code)

Max Activating Token Index: 369

Text #16

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1376. Min Act: -0.0000

Data Index: 52151 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1565321 (Python Code)

Max Activating Token Index: 637

Text #18

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1407. Min Act: -0.0000

Data Index: 1604417 (Python Code)

Max Activating Token Index: 525

Text #19

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1513. Min Act: -0.0000

Data Index: 361633 (C4 (Web Text))

Max Activating Token Index: 275