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

Dataset: The Pile

Neuron 3406 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: 0.2572. Min Range: -0.2572

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1335671 (The Pile)

Max Activating Token Index: 681

Text #1

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2533. Min Act: -0.0000

Data Index: 1553270 (The Pile)

Max Activating Token Index: 195

Text #2

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1471 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1743055 (The Pile)

Max Activating Token Index: 1002

Text #4

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2191. Min Act: -0.0000

Data Index: 3187 (The Pile)

Max Activating Token Index: 988

Text #5

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1903. Min Act: -0.0000

Data Index: 483077 (The Pile)

Max Activating Token Index: 773

Text #6

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1670696 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1577450 (The Pile)

Max Activating Token Index: 536

Text #8

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2309. Min Act: -0.0000

Data Index: 884426 (The Pile)

Max Activating Token Index: 373

Text #9

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2386. Min Act: -0.0000

Data Index: 740163 (The Pile)

Max Activating Token Index: 960

Text #10

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2229. Min Act: -0.0000

Data Index: 583107 (The Pile)

Max Activating Token Index: 346

Text #11

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1395210 (The Pile)

Max Activating Token Index: 484

Text #12

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2006. Min Act: -0.0000

Data Index: 255296 (The Pile)

Max Activating Token Index: 547

Text #13

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1735496 (The Pile)

Max Activating Token Index: 377

Text #14

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2011. Min Act: -0.0000

Data Index: 975598 (The Pile)

Max Activating Token Index: 186

Text #15

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1830. Min Act: -0.0000

Data Index: 426169 (The Pile)

Max Activating Token Index: 459

Text #16

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1530474 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1494067 (The Pile)

Max Activating Token Index: 19

Text #18

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1860. Min Act: -0.0000

Data Index: 858926 (The Pile)

Max Activating Token Index: 847

Text #19

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2122. Min Act: -0.0001

Data Index: 833190 (The Pile)

Max Activating Token Index: 437