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

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

Neuron 1591 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0633. Min Act: -0.0002

Data Index: 359887 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1468218 (Python Code)

Max Activating Token Index: 128

Text #2

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0709. Min Act: -0.0002

Data Index: 937248 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1505599 (Python Code)

Max Activating Token Index: 846

Text #4

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1425555 (Python Code)

Max Activating Token Index: 856

Text #5

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0555. Min Act: -0.0002

Data Index: 897542 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1486711 (Python Code)

Max Activating Token Index: 854

Text #7

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1503264 (Python Code)

Max Activating Token Index: 747

Text #8

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0534. Min Act: -0.0002

Data Index: 854188 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1026569 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1185614 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0488. Min Act: -0.0002

Data Index: 277702 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1610724 (Python Code)

Max Activating Token Index: 466

Text #13

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1602716 (Python Code)

Max Activating Token Index: 764

Text #14

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1427446 (Python Code)

Max Activating Token Index: 853

Text #15

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0467. Min Act: -0.0002

Data Index: 824190 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1432771 (Python Code)

Max Activating Token Index: 741

Text #17

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0445. Min Act: -0.0002

Data Index: 741565 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1614574 (Python Code)

Max Activating Token Index: 728

Text #19

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1469036 (Python Code)

Max Activating Token Index: 484