Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1524 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1616959 (Python Code)

Max Activating Token Index: 101

Text #1

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4968. Min Act: -0.0000

Data Index: 37777 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1533852 (Python Code)

Max Activating Token Index: 356

Text #3

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1483256 (Python Code)

Max Activating Token Index: 230

Text #4

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1474434 (Python Code)

Max Activating Token Index: 579

Text #5

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1569886 (Python Code)

Max Activating Token Index: 860

Text #6

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1637907 (Python Code)

Max Activating Token Index: 715

Text #7

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1651997 (Python Code)

Max Activating Token Index: 320

Text #8

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1644972 (Python Code)

Max Activating Token Index: 43

Text #9

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1375492 (Python Code)

Max Activating Token Index: 307

Text #10

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3332. Min Act: -0.0000

Data Index: 1376056 (Python Code)

Max Activating Token Index: 112

Text #11

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1634469 (Python Code)

Max Activating Token Index: 159

Text #12

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1426111 (Python Code)

Max Activating Token Index: 369

Text #13

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3461. Min Act: -0.0000

Data Index: 499034 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1487365 (Python Code)

Max Activating Token Index: 546

Text #15

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1545462 (Python Code)

Max Activating Token Index: 529

Text #16

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1462988 (Python Code)

Max Activating Token Index: 524

Text #17

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1465981 (Python Code)

Max Activating Token Index: 490

Text #18

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1478893 (Python Code)

Max Activating Token Index: 583

Text #19

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1654108 (Python Code)

Max Activating Token Index: 12