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

Dataset: The Pile

Neuron 4486 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: 0.1292. Min Range: -0.1292

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1981983 (The Pile)

Max Activating Token Index: 201

Text #1

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1292. Min Act: -0.0000

Data Index: 1742442 (The Pile)

Max Activating Token Index: 114

Text #2

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1216307 (The Pile)

Max Activating Token Index: 324

Text #3

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1104. Min Act: -0.0000

Data Index: 877536 (The Pile)

Max Activating Token Index: 83

Text #4

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1039. Min Act: -0.0000

Data Index: 309957 (The Pile)

Max Activating Token Index: 487

Text #5

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1001. Min Act: -0.0000

Data Index: 16173 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1736925 (The Pile)

Max Activating Token Index: 898

Text #7

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1336610 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0989. Min Act: -0.0000

Data Index: 589232 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1070. Min Act: -0.0000

Data Index: 1608122 (The Pile)

Max Activating Token Index: 417

Text #10

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0946. Min Act: -0.0000

Data Index: 699126 (The Pile)

Max Activating Token Index: 215

Text #11

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1483736 (The Pile)

Max Activating Token Index: 111

Text #12

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0971. Min Act: -0.0000

Data Index: 1914349 (The Pile)

Max Activating Token Index: 281

Text #13

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1568637 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0884. Min Act: -0.0000

Data Index: 312749 (The Pile)

Max Activating Token Index: 59

Text #15

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0911. Min Act: -0.0000

Data Index: 48237 (The Pile)

Max Activating Token Index: 53

Text #16

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0898. Min Act: -0.0000

Data Index: 255600 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0927. Min Act: -0.0000

Data Index: 488835 (The Pile)

Max Activating Token Index: 378

Text #18

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1117284 (The Pile)

Max Activating Token Index: 575

Text #19

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0949. Min Act: -0.0000

Data Index: 709608 (The Pile)

Max Activating Token Index: 913