Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3307 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.2822. Min Act: -0.0000

Data Index: 393573 (The Pile)

Max Activating Token Index: 28

Text #1

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.2246. Min Act: -0.0000

Data Index: 243284 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.1974. Min Act: -0.0000

Data Index: 1785537 (The Pile)

Max Activating Token Index: 21

Text #3

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.1592. Min Act: -0.0000

Data Index: 995675 (The Pile)

Max Activating Token Index: 26

Text #4

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.0640. Min Act: -0.0000

Data Index: 463305 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.0029. Min Act: -0.0000

Data Index: 1517935 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.2073. Min Act: -0.0000

Data Index: 355592 (The Pile)

Max Activating Token Index: 30

Text #7

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.9896. Min Act: -0.0000

Data Index: 358806 (The Pile)

Max Activating Token Index: 30

Text #8

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.0519. Min Act: -0.0000

Data Index: 1030234 (The Pile)

Max Activating Token Index: 17

Text #9

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.0408. Min Act: -0.0000

Data Index: 480436 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1303597 (The Pile)

Max Activating Token Index: 21

Text #11

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.1026. Min Act: -0.0000

Data Index: 1502004 (The Pile)

Max Activating Token Index: 28

Text #12

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.0033. Min Act: -0.0000

Data Index: 1308880 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.9869. Min Act: -0.0000

Data Index: 695159 (The Pile)

Max Activating Token Index: 19

Text #14

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.9860. Min Act: -0.0000

Data Index: 901951 (The Pile)

Max Activating Token Index: 19

Text #15

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.0529. Min Act: -0.0000

Data Index: 436065 (The Pile)

Max Activating Token Index: 36

Text #16

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.9764. Min Act: -0.0000

Data Index: 1638645 (The Pile)

Max Activating Token Index: 30

Text #17

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.1028. Min Act: -0.0000

Data Index: 68260 (The Pile)

Max Activating Token Index: 24

Text #18

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.9381. Min Act: -0.0000

Data Index: 1662953 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.0142. Min Act: -0.0000

Data Index: 1989883 (The Pile)

Max Activating Token Index: 20