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

Dataset: The Pile

Neuron 3914 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.1359. Min Act: -0.0000

Data Index: 307515 (The Pile)

Max Activating Token Index: 480

Text #1

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0507. Min Act: -0.0000

Data Index: 1434955 (The Pile)

Max Activating Token Index: 654

Text #2

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0213. Min Act: -0.0000

Data Index: 528985 (The Pile)

Max Activating Token Index: 750

Text #3

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0485. Min Act: -0.0000

Data Index: 1669887 (The Pile)

Max Activating Token Index: 335

Text #4

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0328. Min Act: -0.0000

Data Index: 151874 (The Pile)

Max Activating Token Index: 600

Text #5

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0621. Min Act: -0.0000

Data Index: 1171429 (The Pile)

Max Activating Token Index: 857

Text #6

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1537585 (The Pile)

Max Activating Token Index: 35

Text #7

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0631. Min Act: -0.0000

Data Index: 80929 (The Pile)

Max Activating Token Index: 327

Text #8

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9416. Min Act: -0.0000

Data Index: 362262 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0511. Min Act: -0.0000

Data Index: 795534 (The Pile)

Max Activating Token Index: 880

Text #10

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1442270 (The Pile)

Max Activating Token Index: 394

Text #11

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9943. Min Act: -0.0000

Data Index: 1015191 (The Pile)

Max Activating Token Index: 936

Text #12

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1424671 (The Pile)

Max Activating Token Index: 585

Text #13

Max Range: 1.1359. Min Range: -1.1359

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1200579 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9094. Min Act: -0.0000

Data Index: 969215 (The Pile)

Max Activating Token Index: 770

Text #15

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.7680. Min Act: -0.0000

Data Index: 245223 (The Pile)

Max Activating Token Index: 998

Text #16

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1321808 (The Pile)

Max Activating Token Index: 585

Text #17

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.9190. Min Act: -0.0000

Data Index: 495778 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.8715. Min Act: -0.0000

Data Index: 121705 (The Pile)

Max Activating Token Index: 81

Text #19

Max Range: 1.1359. Min Range: -1.1359

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1547688 (The Pile)

Max Activating Token Index: 334