Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1085 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0608. Min Act: -0.0006

Data Index: 501901 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0575. Min Act: -0.0006

Data Index: 145008 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0567. Min Act: -0.0006

Data Index: 444151 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0571. Min Act: -0.0006

Data Index: 145148 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0569. Min Act: -0.0006

Data Index: 53453 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0546. Min Act: -0.0006

Data Index: 1220667 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0533. Min Act: -0.0006

Data Index: 969226 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0502. Min Act: -0.0006

Data Index: 110280 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0558. Min Act: -0.0006

Data Index: 386783 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0519. Min Act: -0.0006

Data Index: 1239085 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0514. Min Act: -0.0006

Data Index: 138449 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0503. Min Act: -0.0006

Data Index: 232762 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0492. Min Act: -0.0006

Data Index: 88666 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0500. Min Act: -0.0006

Data Index: 394399 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0467. Min Act: -0.0006

Data Index: 510399 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0474. Min Act: -0.0006

Data Index: 1267832 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0508. Min Act: -0.0006

Data Index: 568470 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0494. Min Act: -0.0006

Data Index: 523644 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0491. Min Act: -0.0006

Data Index: 485744 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0490. Min Act: -0.0006

Data Index: 604328 (C4 (Web Text))

Max Activating Token Index: 621