Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3734 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7772. Min Range: -2.7772

Max Act: 2.7772. Min Act: -0.0000

Data Index: 1543159 (Python Code)

Max Activating Token Index: 110

Text #1

Max Range: 2.7772. Min Range: -2.7772

Max Act: 2.5241. Min Act: -0.0000

Data Index: 1501393 (Python Code)

Max Activating Token Index: 882

Text #2

Max Range: 2.7772. Min Range: -2.7772

Max Act: 2.1130. Min Act: -0.0000

Data Index: 1559670 (Python Code)

Max Activating Token Index: 221

Text #3

Max Range: 2.7772. Min Range: -2.7772

Max Act: 2.0577. Min Act: -0.0000

Data Index: 1620992 (Python Code)

Max Activating Token Index: 886

Text #4

Max Range: 2.7772. Min Range: -2.7772

Max Act: 2.2407. Min Act: -0.0000

Data Index: 1437421 (Python Code)

Max Activating Token Index: 331

Text #5

Max Range: 2.7772. Min Range: -2.7772

Max Act: 2.0712. Min Act: -0.0000

Data Index: 1520043 (Python Code)

Max Activating Token Index: 241

Text #6

Max Range: 2.7772. Min Range: -2.7772

Max Act: 2.0921. Min Act: -0.0000

Data Index: 1518280 (Python Code)

Max Activating Token Index: 913

Text #7

Max Range: 2.7772. Min Range: -2.7772

Max Act: 1.8345. Min Act: -0.0000

Data Index: 1549909 (Python Code)

Max Activating Token Index: 839

Text #8

Max Range: 2.7772. Min Range: -2.7772

Max Act: 1.8960. Min Act: -0.0000

Data Index: 1582695 (Python Code)

Max Activating Token Index: 554

Text #9

Max Range: 2.7772. Min Range: -2.7772

Max Act: 1.7900. Min Act: -0.0000

Data Index: 1375169 (Python Code)

Max Activating Token Index: 586

Text #10

Max Range: 2.7772. Min Range: -2.7772

Max Act: 1.9551. Min Act: -0.0000

Data Index: 1639629 (Python Code)

Max Activating Token Index: 329

Text #11

Max Range: 2.7772. Min Range: -2.7772

Max Act: 1.8477. Min Act: -0.0000

Data Index: 1431474 (Python Code)

Max Activating Token Index: 967

Text #12

Max Range: 2.7772. Min Range: -2.7772

Max Act: 1.8312. Min Act: -0.0000

Data Index: 1466209 (Python Code)

Max Activating Token Index: 432

Text #13

Max Range: 2.7772. Min Range: -2.7772

Max Act: 1.9088. Min Act: -0.0000

Data Index: 1369421 (Python Code)

Max Activating Token Index: 1018

Text #14

Max Range: 2.7772. Min Range: -2.7772

Max Act: 1.7748. Min Act: -0.0000

Data Index: 1405482 (Python Code)

Max Activating Token Index: 465

Text #15

Max Range: 2.7772. Min Range: -2.7772

Max Act: 1.7518. Min Act: -0.0000

Data Index: 1564335 (Python Code)

Max Activating Token Index: 933

Text #16

Max Range: 2.7772. Min Range: -2.7772

Max Act: 1.7424. Min Act: -0.0000

Data Index: 1523895 (Python Code)

Max Activating Token Index: 507

Text #17

Max Range: 2.7772. Min Range: -2.7772

Max Act: 1.7332. Min Act: -0.0000

Data Index: 1535951 (Python Code)

Max Activating Token Index: 280

Text #18

Max Range: 2.7772. Min Range: -2.7772

Max Act: 1.6937. Min Act: -0.0000

Data Index: 1416368 (Python Code)

Max Activating Token Index: 804

Text #19

Max Range: 2.7772. Min Range: -2.7772

Max Act: 1.7010. Min Act: -0.0000

Data Index: 1371386 (Python Code)

Max Activating Token Index: 435