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

Dataset: The Pile

Neuron 2983 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.4735. Min Act: -0.0000

Data Index: 1254257 (The Pile)

Max Activating Token Index: 866

Text #1

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.5060. Min Act: -0.0000

Data Index: 171768 (The Pile)

Max Activating Token Index: 154

Text #2

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.4374. Min Act: -0.0000

Data Index: 1322091 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.1159. Min Act: -0.0000

Data Index: 830101 (The Pile)

Max Activating Token Index: 237

Text #4

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.4349. Min Act: -0.0000

Data Index: 325301 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.1709. Min Act: -0.0000

Data Index: 628325 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3001. Min Act: -0.0000

Data Index: 1960710 (The Pile)

Max Activating Token Index: 863

Text #7

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.0464. Min Act: -0.0000

Data Index: 1652194 (The Pile)

Max Activating Token Index: 689

Text #8

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.1644. Min Act: -0.0000

Data Index: 1156502 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3075. Min Act: -0.0000

Data Index: 91025 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.1712. Min Act: -0.0000

Data Index: 1643708 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 3.5060. Min Range: -3.5060

Max Act: 2.9980. Min Act: -0.0000

Data Index: 1126637 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 3.5060. Min Range: -3.5060

Max Act: 2.9751. Min Act: -0.0000

Data Index: 1429630 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.1021. Min Act: -0.0000

Data Index: 458782 (The Pile)

Max Activating Token Index: 432

Text #14

Max Range: 3.5060. Min Range: -3.5060

Max Act: 2.6634. Min Act: -0.0000

Data Index: 32054 (The Pile)

Max Activating Token Index: 961

Text #15

Max Range: 3.5060. Min Range: -3.5060

Max Act: 2.8980. Min Act: -0.0000

Data Index: 408554 (The Pile)

Max Activating Token Index: 949

Text #16

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.0131. Min Act: -0.0000

Data Index: 403853 (The Pile)

Max Activating Token Index: 542

Text #17

Max Range: 3.5060. Min Range: -3.5060

Max Act: 2.6125. Min Act: -0.0000

Data Index: 1385751 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.0161. Min Act: -0.0000

Data Index: 1182837 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 3.5060. Min Range: -3.5060

Max Act: 2.9518. Min Act: -0.0000

Data Index: 122493 (The Pile)

Max Activating Token Index: 922