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

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

Neuron 4147 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1400926 (Python Code)

Max Activating Token Index: 470

Text #1

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1535565 (Python Code)

Max Activating Token Index: 325

Text #2

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0700. Min Act: -0.0000

Data Index: 1491248 (Python Code)

Max Activating Token Index: 213

Text #3

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0711. Min Act: -0.0000

Data Index: 1365143 (Python Code)

Max Activating Token Index: 510

Text #4

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1393143 (Python Code)

Max Activating Token Index: 803

Text #5

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1589891 (Python Code)

Max Activating Token Index: 510

Text #6

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1621154 (Python Code)

Max Activating Token Index: 329

Text #7

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1502633 (Python Code)

Max Activating Token Index: 100

Text #8

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0582. Min Act: -0.0000

Data Index: 1540633 (Python Code)

Max Activating Token Index: 962

Text #9

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0663. Min Act: -0.0000

Data Index: 1365438 (Python Code)

Max Activating Token Index: 714

Text #10

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0639. Min Act: -0.0000

Data Index: 1404612 (Python Code)

Max Activating Token Index: 655

Text #11

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0636. Min Act: -0.0000

Data Index: 1522612 (Python Code)

Max Activating Token Index: 73

Text #12

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1596061 (Python Code)

Max Activating Token Index: 973

Text #13

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0614. Min Act: -0.0000

Data Index: 1421905 (Python Code)

Max Activating Token Index: 269

Text #14

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1580552 (Python Code)

Max Activating Token Index: 547

Text #15

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0661. Min Act: -0.0000

Data Index: 1623029 (Python Code)

Max Activating Token Index: 1006

Text #16

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0583. Min Act: -0.0000

Data Index: 1648466 (Python Code)

Max Activating Token Index: 562

Text #17

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0599. Min Act: -0.0000

Data Index: 1500905 (Python Code)

Max Activating Token Index: 561

Text #18

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0552. Min Act: -0.0000

Data Index: 1445291 (Python Code)

Max Activating Token Index: 692

Text #19

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1423470 (Python Code)

Max Activating Token Index: 877