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

Dataset: The Pile

Neuron 553 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.9162. Min Act: -0.0000

Data Index: 1892787 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.6967. Min Act: -0.0000

Data Index: 1908988 (The Pile)

Max Activating Token Index: 378

Text #2

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.7299. Min Act: -0.0000

Data Index: 660073 (The Pile)

Max Activating Token Index: 654

Text #3

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.6211. Min Act: -0.0000

Data Index: 158849 (The Pile)

Max Activating Token Index: 56

Text #4

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.5671. Min Act: -0.0000

Data Index: 1630686 (The Pile)

Max Activating Token Index: 872

Text #5

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4884. Min Act: -0.0000

Data Index: 1774449 (The Pile)

Max Activating Token Index: 632

Text #6

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.5521. Min Act: -0.0000

Data Index: 893671 (The Pile)

Max Activating Token Index: 626

Text #7

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4944. Min Act: -0.0000

Data Index: 1147481 (The Pile)

Max Activating Token Index: 132

Text #8

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4251. Min Act: -0.0000

Data Index: 1462464 (The Pile)

Max Activating Token Index: 694

Text #9

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.5824. Min Act: -0.0000

Data Index: 1934454 (The Pile)

Max Activating Token Index: 61

Text #10

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4330. Min Act: -0.0000

Data Index: 220953 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.3329. Min Act: -0.0000

Data Index: 247851 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4058. Min Act: -0.0000

Data Index: 465875 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4044. Min Act: -0.0000

Data Index: 920265 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4595. Min Act: -0.0000

Data Index: 231523 (The Pile)

Max Activating Token Index: 935

Text #15

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.3616. Min Act: -0.0000

Data Index: 1976195 (The Pile)

Max Activating Token Index: 832

Text #16

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1750039 (The Pile)

Max Activating Token Index: 840

Text #17

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4071. Min Act: -0.0000

Data Index: 713258 (The Pile)

Max Activating Token Index: 244

Text #18

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.2310. Min Act: -0.0000

Data Index: 990871 (The Pile)

Max Activating Token Index: 881

Text #19

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.3391. Min Act: -0.0000

Data Index: 1097595 (The Pile)

Max Activating Token Index: 681