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

Dataset: The Pile

Neuron 1705 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: 0.7688. Min Range: -0.7688

Max Act: 0.7663. Min Act: -0.0000

Data Index: 537486 (The Pile)

Max Activating Token Index: 8

Text #1

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1147192 (The Pile)

Max Activating Token Index: 161

Text #2

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7688. Min Act: -0.0000

Data Index: 322837 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7023. Min Act: -0.0000

Data Index: 195860 (The Pile)

Max Activating Token Index: 590

Text #4

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1737057 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1806798 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1863909 (The Pile)

Max Activating Token Index: 275

Text #7

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6054. Min Act: -0.0000

Data Index: 202688 (The Pile)

Max Activating Token Index: 708

Text #8

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1988470 (The Pile)

Max Activating Token Index: 304

Text #9

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1613744 (The Pile)

Max Activating Token Index: 106

Text #10

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6245. Min Act: -0.0000

Data Index: 790373 (The Pile)

Max Activating Token Index: 180

Text #11

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6205. Min Act: -0.0000

Data Index: 565559 (The Pile)

Max Activating Token Index: 86

Text #12

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6259. Min Act: -0.0000

Data Index: 936346 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1433200 (The Pile)

Max Activating Token Index: 687

Text #14

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6086. Min Act: -0.0000

Data Index: 193258 (The Pile)

Max Activating Token Index: 38

Text #15

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1738614 (The Pile)

Max Activating Token Index: 122

Text #16

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1014221 (The Pile)

Max Activating Token Index: 220

Text #17

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1803982 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5772. Min Act: -0.0000

Data Index: 784909 (The Pile)

Max Activating Token Index: 457

Text #19

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1633056 (The Pile)

Max Activating Token Index: 311