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

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

Neuron 160 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1525317 (Python Code)

Max Activating Token Index: 583

Text #1

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1378880 (Python Code)

Max Activating Token Index: 496

Text #2

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.6191. Min Act: -0.0000

Data Index: 797095 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1650134 (Python Code)

Max Activating Token Index: 801

Text #4

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1468009 (Python Code)

Max Activating Token Index: 766

Text #5

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1580383 (Python Code)

Max Activating Token Index: 565

Text #6

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1553478 (Python Code)

Max Activating Token Index: 698

Text #7

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1453646 (Python Code)

Max Activating Token Index: 848

Text #8

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1594473 (Python Code)

Max Activating Token Index: 927

Text #9

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1360022 (Python Code)

Max Activating Token Index: 992

Text #10

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1653053 (Python Code)

Max Activating Token Index: 717

Text #11

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1609586 (Python Code)

Max Activating Token Index: 751

Text #12

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1645887 (Python Code)

Max Activating Token Index: 564

Text #13

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5664. Min Act: 0.0000

Data Index: 1411417 (Python Code)

Max Activating Token Index: 389

Text #14

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1375001 (Python Code)

Max Activating Token Index: 600

Text #15

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1645628 (Python Code)

Max Activating Token Index: 579

Text #16

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1402555 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1476651 (Python Code)

Max Activating Token Index: 804

Text #18

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1489582 (Python Code)

Max Activating Token Index: 699

Text #19

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1632876 (Python Code)

Max Activating Token Index: 441