Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 647 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1451520 (Python Code)

Max Activating Token Index: 582

Text #1

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0562. Min Act: -0.0003

Data Index: 1599945 (Python Code)

Max Activating Token Index: 111

Text #2

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1570376 (Python Code)

Max Activating Token Index: 628

Text #3

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0502. Min Act: -0.0003

Data Index: 996860 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0478. Min Act: -0.0003

Data Index: 1374133 (Python Code)

Max Activating Token Index: 751

Text #5

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0461. Min Act: -0.0003

Data Index: 632159 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1368465 (Python Code)

Max Activating Token Index: 387

Text #7

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1412193 (Python Code)

Max Activating Token Index: 984

Text #8

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1656313 (Python Code)

Max Activating Token Index: 707

Text #9

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1628200 (Python Code)

Max Activating Token Index: 702

Text #10

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1632537 (Python Code)

Max Activating Token Index: 579

Text #11

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0444. Min Act: -0.0003

Data Index: 558995 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0441. Min Act: -0.0004

Data Index: 657408 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1538612 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0440. Min Act: -0.0003

Data Index: 739041 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0428. Min Act: -0.0003

Data Index: 1007643 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0443. Min Act: -0.0003

Data Index: 1452386 (Python Code)

Max Activating Token Index: 304

Text #17

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0447. Min Act: -0.0004

Data Index: 523984 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1458811 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0429. Min Act: -0.0003

Data Index: 430385 (C4 (Web Text))

Max Activating Token Index: 820