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

Dataset: The Pile

Neuron 1172 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: 1.0115. Min Range: -1.0115

Max Act: 1.0115. Min Act: -0.0000

Data Index: 328359 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.9036. Min Act: -0.0000

Data Index: 1562697 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7562. Min Act: -0.0000

Data Index: 518332 (The Pile)

Max Activating Token Index: 196

Text #3

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1679172 (The Pile)

Max Activating Token Index: 558

Text #4

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7436. Min Act: -0.0000

Data Index: 83820 (The Pile)

Max Activating Token Index: 56

Text #5

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1607913 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7313. Min Act: -0.0000

Data Index: 446910 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7771. Min Act: 0.0000

Data Index: 111522 (The Pile)

Max Activating Token Index: 438

Text #8

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1681774 (The Pile)

Max Activating Token Index: 703

Text #9

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1469741 (The Pile)

Max Activating Token Index: 378

Text #10

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6336. Min Act: 0.0000

Data Index: 1301917 (The Pile)

Max Activating Token Index: 690

Text #11

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1824822 (The Pile)

Max Activating Token Index: 831

Text #12

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6149. Min Act: -0.0000

Data Index: 64608 (The Pile)

Max Activating Token Index: 623

Text #13

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1166233 (The Pile)

Max Activating Token Index: 811

Text #14

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1053968 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1165757 (The Pile)

Max Activating Token Index: 793

Text #16

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6570. Min Act: 0.0000

Data Index: 1279306 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6570. Min Act: 0.0000

Data Index: 1708881 (The Pile)

Max Activating Token Index: 24

Text #18

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1851065 (The Pile)

Max Activating Token Index: 798

Text #19

Max Range: 1.0115. Min Range: -1.0115

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1009655 (The Pile)

Max Activating Token Index: 449