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

Dataset: The Pile

Neuron 4469 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1819035 (The Pile)

Max Activating Token Index: 369

Text #1

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3448. Min Act: -0.0000

Data Index: 549623 (The Pile)

Max Activating Token Index: 315

Text #2

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1122139 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3342. Min Act: -0.0000

Data Index: 622652 (The Pile)

Max Activating Token Index: 247

Text #4

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3093. Min Act: 0.0000

Data Index: 1500510 (The Pile)

Max Activating Token Index: 522

Text #5

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2834. Min Act: -0.0000

Data Index: 858593 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1173991 (The Pile)

Max Activating Token Index: 656

Text #7

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1505972 (The Pile)

Max Activating Token Index: 530

Text #8

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2867. Min Act: -0.0000

Data Index: 282760 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2622. Min Act: -0.0000

Data Index: 320299 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2792. Min Act: -0.0000

Data Index: 971882 (The Pile)

Max Activating Token Index: 454

Text #11

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1276042 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2592. Min Act: -0.0000

Data Index: 684960 (The Pile)

Max Activating Token Index: 822

Text #13

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2561. Min Act: -0.0000

Data Index: 1758748 (The Pile)

Max Activating Token Index: 435

Text #14

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2631. Min Act: -0.0000

Data Index: 444993 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1318492 (The Pile)

Max Activating Token Index: 454

Text #16

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2481. Min Act: -0.0000

Data Index: 939723 (The Pile)

Max Activating Token Index: 900

Text #17

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2618. Min Act: -0.0000

Data Index: 293851 (The Pile)

Max Activating Token Index: 378

Text #18

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1394303 (The Pile)

Max Activating Token Index: 648

Text #19

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1730472 (The Pile)

Max Activating Token Index: 355