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

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

Neuron 3132 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: 0.0719. Min Range: -0.0719

Max Act: 0.0719. Min Act: -0.0002

Data Index: 490517 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0669. Min Act: -0.0002

Data Index: 215923 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0595. Min Act: -0.0002

Data Index: 974664 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0571. Min Act: -0.0002

Data Index: 568421 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1257533 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1179901 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0544. Min Act: -0.0002

Data Index: 16410 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1289580 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1234612 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1223105 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0538. Min Act: -0.0002

Data Index: 952184 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0535. Min Act: -0.0002

Data Index: 585156 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0531. Min Act: -0.0002

Data Index: 646246 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0522. Min Act: -0.0002

Data Index: 917379 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1116114 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0470. Min Act: -0.0002

Data Index: 465411 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0510. Min Act: -0.0002

Data Index: 971954 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1185282 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0499. Min Act: -0.0002

Data Index: 884299 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0503. Min Act: -0.0002

Data Index: 576619 (C4 (Web Text))

Max Activating Token Index: 37