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

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

Neuron 1809 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6509. Min Range: -5.6509

Max Act: 5.6509. Min Act: -0.0000

Data Index: 1635371 (Python Code)

Max Activating Token Index: 84

Text #1

Max Range: 5.6509. Min Range: -5.6509

Max Act: 4.0553. Min Act: -0.0000

Data Index: 1550313 (Python Code)

Max Activating Token Index: 387

Text #2

Max Range: 5.6509. Min Range: -5.6509

Max Act: 3.6834. Min Act: -0.0000

Data Index: 1426283 (Python Code)

Max Activating Token Index: 258

Text #3

Max Range: 5.6509. Min Range: -5.6509

Max Act: 3.9434. Min Act: -0.0000

Data Index: 1488785 (Python Code)

Max Activating Token Index: 353

Text #4

Max Range: 5.6509. Min Range: -5.6509

Max Act: 3.2435. Min Act: -0.0000

Data Index: 1368565 (Python Code)

Max Activating Token Index: 916

Text #5

Max Range: 5.6509. Min Range: -5.6509

Max Act: 3.2138. Min Act: -0.0000

Data Index: 1641269 (Python Code)

Max Activating Token Index: 412

Text #6

Max Range: 5.6509. Min Range: -5.6509

Max Act: 3.2870. Min Act: -0.0000

Data Index: 1505364 (Python Code)

Max Activating Token Index: 421

Text #7

Max Range: 5.6509. Min Range: -5.6509

Max Act: 3.4697. Min Act: -0.0000

Data Index: 1375330 (Python Code)

Max Activating Token Index: 274

Text #8

Max Range: 5.6509. Min Range: -5.6509

Max Act: 3.3796. Min Act: -0.0000

Data Index: 1615796 (Python Code)

Max Activating Token Index: 78

Text #9

Max Range: 5.6509. Min Range: -5.6509

Max Act: 3.1861. Min Act: -0.0000

Data Index: 1487292 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 5.6509. Min Range: -5.6509

Max Act: 3.1615. Min Act: -0.0000

Data Index: 1571760 (Python Code)

Max Activating Token Index: 667

Text #11

Max Range: 5.6509. Min Range: -5.6509

Max Act: 3.1156. Min Act: -0.0000

Data Index: 1440383 (Python Code)

Max Activating Token Index: 986

Text #12

Max Range: 5.6509. Min Range: -5.6509

Max Act: 3.2302. Min Act: -0.0000

Data Index: 1650187 (Python Code)

Max Activating Token Index: 814

Text #13

Max Range: 5.6509. Min Range: -5.6509

Max Act: 2.8787. Min Act: -0.0000

Data Index: 1476550 (Python Code)

Max Activating Token Index: 180

Text #14

Max Range: 5.6509. Min Range: -5.6509

Max Act: 2.8438. Min Act: -0.0000

Data Index: 1543810 (Python Code)

Max Activating Token Index: 595

Text #15

Max Range: 5.6509. Min Range: -5.6509

Max Act: 2.8329. Min Act: -0.0000

Data Index: 1504887 (Python Code)

Max Activating Token Index: 19

Text #16

Max Range: 5.6509. Min Range: -5.6509

Max Act: 3.1861. Min Act: -0.0000

Data Index: 1608675 (Python Code)

Max Activating Token Index: 844

Text #17

Max Range: 5.6509. Min Range: -5.6509

Max Act: 2.7334. Min Act: -0.0000

Data Index: 1480215 (Python Code)

Max Activating Token Index: 378

Text #18

Max Range: 5.6509. Min Range: -5.6509

Max Act: 2.8371. Min Act: -0.0000

Data Index: 1639260 (Python Code)

Max Activating Token Index: 490

Text #19

Max Range: 5.6509. Min Range: -5.6509

Max Act: 2.8074. Min Act: -0.0000

Data Index: 1599594 (Python Code)

Max Activating Token Index: 178