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

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

Neuron 4183 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: 0.7056. Min Range: -0.7056

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1448793 (Python Code)

Max Activating Token Index: 954

Text #1

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1536479 (Python Code)

Max Activating Token Index: 674

Text #2

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.6348. Min Act: -0.0000

Data Index: 891288 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1626453 (Python Code)

Max Activating Token Index: 547

Text #4

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5881. Min Act: -0.0000

Data Index: 351214 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1392840 (Python Code)

Max Activating Token Index: 196

Text #6

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5452. Min Act: -0.0000

Data Index: 1419425 (Python Code)

Max Activating Token Index: 867

Text #7

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1456960 (Python Code)

Max Activating Token Index: 327

Text #8

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1565620 (Python Code)

Max Activating Token Index: 461

Text #9

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5655. Min Act: -0.0000

Data Index: 1389561 (Python Code)

Max Activating Token Index: 599

Text #10

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1370017 (Python Code)

Max Activating Token Index: 881

Text #11

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1392503 (Python Code)

Max Activating Token Index: 155

Text #12

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1505894 (Python Code)

Max Activating Token Index: 643

Text #13

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1579539 (Python Code)

Max Activating Token Index: 355

Text #14

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1576516 (Python Code)

Max Activating Token Index: 331

Text #15

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1541838 (Python Code)

Max Activating Token Index: 442

Text #16

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1385428 (Python Code)

Max Activating Token Index: 508

Text #17

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1449442 (Python Code)

Max Activating Token Index: 935

Text #18

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1473584 (Python Code)

Max Activating Token Index: 299

Text #19

Max Range: 0.7056. Min Range: -0.7056

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1581442 (Python Code)

Max Activating Token Index: 446