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

Dataset: The Pile

Neuron 2772 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.6696. Min Range: -8.6696

Max Act: 8.6696. Min Act: -0.0000

Data Index: 906129 (The Pile)

Max Activating Token Index: 735

Text #1

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.8393. Min Act: -0.0000

Data Index: 1023258 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.7407. Min Act: -0.0000

Data Index: 1737126 (The Pile)

Max Activating Token Index: 502

Text #3

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.9016. Min Act: -0.0000

Data Index: 1969163 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.8396. Min Act: -0.0000

Data Index: 1361609 (The Pile)

Max Activating Token Index: 778

Text #5

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.7769. Min Act: -0.0000

Data Index: 534010 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.6563. Min Act: -0.0000

Data Index: 535443 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.6014. Min Act: -0.0000

Data Index: 1510532 (The Pile)

Max Activating Token Index: 999

Text #8

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.2698. Min Act: -0.0000

Data Index: 1928589 (The Pile)

Max Activating Token Index: 831

Text #9

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.6315. Min Act: -0.0000

Data Index: 837085 (The Pile)

Max Activating Token Index: 707

Text #10

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.6177. Min Act: -0.0000

Data Index: 358520 (The Pile)

Max Activating Token Index: 557

Text #11

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.5788. Min Act: -0.0000

Data Index: 1623320 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.5969. Min Act: -0.0000

Data Index: 993033 (The Pile)

Max Activating Token Index: 928

Text #13

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.4018. Min Act: -0.0000

Data Index: 1543554 (The Pile)

Max Activating Token Index: 188

Text #14

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.5850. Min Act: -0.0000

Data Index: 1002492 (The Pile)

Max Activating Token Index: 765

Text #15

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.3495. Min Act: -0.0000

Data Index: 1484525 (The Pile)

Max Activating Token Index: 711

Text #16

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.5000. Min Act: -0.0000

Data Index: 716254 (The Pile)

Max Activating Token Index: 456

Text #17

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.4896. Min Act: -0.0000

Data Index: 636617 (The Pile)

Max Activating Token Index: 911

Text #18

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.6571. Min Act: -0.0000

Data Index: 1461266 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 8.6696. Min Range: -8.6696

Max Act: 7.3881. Min Act: -0.0000

Data Index: 74574 (The Pile)

Max Activating Token Index: 915