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

Dataset: The Pile

Neuron 4976 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0029. Min Range: -1.0029

Max Act: 1.0029. Min Act: 0.0000

Data Index: 1584274 (The Pile)

Max Activating Token Index: 513

Text #1

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.9566. Min Act: -0.0000

Data Index: 387637 (The Pile)

Max Activating Token Index: 606

Text #2

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.8720. Min Act: 0.0000

Data Index: 1640537 (The Pile)

Max Activating Token Index: 83

Text #3

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.9156. Min Act: -0.0000

Data Index: 938979 (The Pile)

Max Activating Token Index: 405

Text #4

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.9102. Min Act: 0.0000

Data Index: 34827 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.9121. Min Act: -0.0000

Data Index: 1441955 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.8929. Min Act: -0.0000

Data Index: 1479991 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.7776. Min Act: -0.0000

Data Index: 673848 (The Pile)

Max Activating Token Index: 845

Text #8

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1391116 (The Pile)

Max Activating Token Index: 743

Text #9

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.8129. Min Act: -0.0000

Data Index: 223770 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.8160. Min Act: -0.0000

Data Index: 783638 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.7578. Min Act: -0.0000

Data Index: 36989 (The Pile)

Max Activating Token Index: 436

Text #12

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1243085 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.7913. Min Act: -0.0000

Data Index: 333976 (The Pile)

Max Activating Token Index: 538

Text #14

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.7913. Min Act: 0.0000

Data Index: 1392218 (The Pile)

Max Activating Token Index: 37

Text #15

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.7761. Min Act: -0.0000

Data Index: 53884 (The Pile)

Max Activating Token Index: 599

Text #16

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.8207. Min Act: -0.0000

Data Index: 262352 (The Pile)

Max Activating Token Index: 495

Text #17

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.7755. Min Act: -0.0000

Data Index: 479475 (The Pile)

Max Activating Token Index: 407

Text #18

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.7696. Min Act: -0.0000

Data Index: 312123 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 1.0029. Min Range: -1.0029

Max Act: 0.7630. Min Act: -0.0000

Data Index: 726896 (The Pile)

Max Activating Token Index: 341