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

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

Neuron 1958 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8582. Min Act: -0.0003

Data Index: 1443939 (Python Code)

Max Activating Token Index: 406

Text #1

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8253. Min Act: -0.0003

Data Index: 1595760 (Python Code)

Max Activating Token Index: 568

Text #2

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7960. Min Act: -0.0003

Data Index: 1374771 (Python Code)

Max Activating Token Index: 276

Text #3

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7968. Min Act: -0.0003

Data Index: 1426691 (Python Code)

Max Activating Token Index: 765

Text #4

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7354. Min Act: -0.0003

Data Index: 1448826 (Python Code)

Max Activating Token Index: 458

Text #5

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7348. Min Act: -0.0003

Data Index: 1652763 (Python Code)

Max Activating Token Index: 481

Text #6

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7574. Min Act: -0.0003

Data Index: 1484276 (Python Code)

Max Activating Token Index: 241

Text #7

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7222. Min Act: -0.0003

Data Index: 1544883 (Python Code)

Max Activating Token Index: 101

Text #8

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7687. Min Act: -0.0003

Data Index: 1440469 (Python Code)

Max Activating Token Index: 593

Text #9

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7313. Min Act: -0.0003

Data Index: 1489640 (Python Code)

Max Activating Token Index: 541

Text #10

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7289. Min Act: -0.0003

Data Index: 1548836 (Python Code)

Max Activating Token Index: 420

Text #11

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7665. Min Act: -0.0003

Data Index: 1403552 (Python Code)

Max Activating Token Index: 653

Text #12

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7211. Min Act: -0.0003

Data Index: 1415892 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7470. Min Act: -0.0003

Data Index: 1396788 (Python Code)

Max Activating Token Index: 245

Text #14

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7496. Min Act: -0.0003

Data Index: 1590747 (Python Code)

Max Activating Token Index: 139

Text #15

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7414. Min Act: -0.0003

Data Index: 1543458 (Python Code)

Max Activating Token Index: 333

Text #16

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6899. Min Act: -0.0003

Data Index: 1565531 (Python Code)

Max Activating Token Index: 979

Text #17

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7311. Min Act: -0.0003

Data Index: 1629097 (Python Code)

Max Activating Token Index: 163

Text #18

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7265. Min Act: -0.0003

Data Index: 1506810 (Python Code)

Max Activating Token Index: 65

Text #19

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6941. Min Act: -0.0003

Data Index: 1576513 (Python Code)

Max Activating Token Index: 308