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

Dataset: The Pile

Neuron 1085 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: 0.7844. Min Range: -0.7844

Max Act: 0.7844. Min Act: -0.0000

Data Index: 1388333 (The Pile)

Max Activating Token Index: 371

Text #1

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1442254 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5816. Min Act: -0.0000

Data Index: 13864 (The Pile)

Max Activating Token Index: 378

Text #3

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1731334 (The Pile)

Max Activating Token Index: 943

Text #4

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1108954 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1671488 (The Pile)

Max Activating Token Index: 130

Text #6

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1164730 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5206. Min Act: -0.0000

Data Index: 986060 (The Pile)

Max Activating Token Index: 197

Text #8

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4744. Min Act: -0.0000

Data Index: 6805 (The Pile)

Max Activating Token Index: 21

Text #9

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1805009 (The Pile)

Max Activating Token Index: 892

Text #10

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5337. Min Act: -0.0000

Data Index: 863476 (The Pile)

Max Activating Token Index: 953

Text #11

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4818. Min Act: -0.0000

Data Index: 92961 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4854. Min Act: -0.0000

Data Index: 132235 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5009. Min Act: -0.0000

Data Index: 545379 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4997. Min Act: -0.0000

Data Index: 53226 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1686884 (The Pile)

Max Activating Token Index: 452

Text #16

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1401972 (The Pile)

Max Activating Token Index: 43

Text #17

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1843828 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5248. Min Act: -0.0000

Data Index: 468821 (The Pile)

Max Activating Token Index: 616

Text #19

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4769. Min Act: -0.0000

Data Index: 87576 (The Pile)

Max Activating Token Index: 826