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

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

Neuron 1726 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0886. Min Range: -2.0886

Max Act: 2.0886. Min Act: -0.0000

Data Index: 1641112 (Python Code)

Max Activating Token Index: 502

Text #1

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.3511. Min Act: -0.0000

Data Index: 1553968 (Python Code)

Max Activating Token Index: 287

Text #2

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.3014. Min Act: -0.0000

Data Index: 1615958 (Python Code)

Max Activating Token Index: 911

Text #3

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.9615. Min Act: -0.0000

Data Index: 1574831 (Python Code)

Max Activating Token Index: 384

Text #4

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1618552 (Python Code)

Max Activating Token Index: 813

Text #5

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1421881 (Python Code)

Max Activating Token Index: 800

Text #6

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1634832 (Python Code)

Max Activating Token Index: 740

Text #7

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1493773 (Python Code)

Max Activating Token Index: 825

Text #8

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1411371 (Python Code)

Max Activating Token Index: 716

Text #9

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.8640. Min Act: -0.0000

Data Index: 1523779 (Python Code)

Max Activating Token Index: 566

Text #10

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1454440 (Python Code)

Max Activating Token Index: 224

Text #11

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1554172 (Python Code)

Max Activating Token Index: 276

Text #12

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1622006 (Python Code)

Max Activating Token Index: 378

Text #13

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1593845 (Python Code)

Max Activating Token Index: 482

Text #14

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1429320 (Python Code)

Max Activating Token Index: 741

Text #15

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1378361 (Python Code)

Max Activating Token Index: 423

Text #16

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1601356 (Python Code)

Max Activating Token Index: 725

Text #17

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1541248 (Python Code)

Max Activating Token Index: 445

Text #18

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1489917 (Python Code)

Max Activating Token Index: 801

Text #19

Max Range: 2.0886. Min Range: -2.0886

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1477060 (Python Code)

Max Activating Token Index: 380