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

Dataset: The Pile

Neuron 3561 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: 1.6683. Min Range: -1.6683

Max Act: 1.6683. Min Act: -0.0000

Data Index: 1193105 (The Pile)

Max Activating Token Index: 924

Text #1

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.4766. Min Act: -0.0000

Data Index: 321152 (The Pile)

Max Activating Token Index: 329

Text #2

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1529461 (The Pile)

Max Activating Token Index: 691

Text #3

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.3679. Min Act: -0.0000

Data Index: 325175 (The Pile)

Max Activating Token Index: 532

Text #4

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.2244. Min Act: -0.0000

Data Index: 1169888 (The Pile)

Max Activating Token Index: 922

Text #5

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.1197. Min Act: -0.0000

Data Index: 813413 (The Pile)

Max Activating Token Index: 840

Text #6

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.2706. Min Act: -0.0000

Data Index: 67203 (The Pile)

Max Activating Token Index: 866

Text #7

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.3212. Min Act: -0.0000

Data Index: 1098163 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.3592. Min Act: -0.0000

Data Index: 1501590 (The Pile)

Max Activating Token Index: 571

Text #9

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.2246. Min Act: -0.0000

Data Index: 1441564 (The Pile)

Max Activating Token Index: 740

Text #10

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.1794. Min Act: -0.0000

Data Index: 441497 (The Pile)

Max Activating Token Index: 549

Text #11

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.2644. Min Act: -0.0000

Data Index: 318378 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.3104. Min Act: -0.0000

Data Index: 1357492 (The Pile)

Max Activating Token Index: 924

Text #13

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.1322. Min Act: -0.0000

Data Index: 768356 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.1005. Min Act: -0.0000

Data Index: 1904114 (The Pile)

Max Activating Token Index: 815

Text #15

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.0900. Min Act: -0.0000

Data Index: 615593 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.1968. Min Act: -0.0000

Data Index: 444154 (The Pile)

Max Activating Token Index: 138

Text #17

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.1699. Min Act: -0.0000

Data Index: 1505985 (The Pile)

Max Activating Token Index: 42

Text #18

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.1645. Min Act: -0.0000

Data Index: 1167791 (The Pile)

Max Activating Token Index: 86

Text #19

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.1934. Min Act: -0.0000

Data Index: 310541 (The Pile)

Max Activating Token Index: 754