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

Dataset: The Pile

Neuron 323 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: 1.2276. Min Range: -1.2276

Max Act: 1.2276. Min Act: -0.0000

Data Index: 1689501 (The Pile)

Max Activating Token Index: 866

Text #1

Max Range: 1.2276. Min Range: -1.2276

Max Act: 1.1377. Min Act: -0.0000

Data Index: 1448867 (The Pile)

Max Activating Token Index: 661

Text #2

Max Range: 1.2276. Min Range: -1.2276

Max Act: 1.0210. Min Act: -0.0000

Data Index: 1612807 (The Pile)

Max Activating Token Index: 31

Text #3

Max Range: 1.2276. Min Range: -1.2276

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1283548 (The Pile)

Max Activating Token Index: 627

Text #4

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8329. Min Act: -0.0000

Data Index: 633321 (The Pile)

Max Activating Token Index: 924

Text #5

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9991. Min Act: -0.0000

Data Index: 1881878 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9771. Min Act: -0.0000

Data Index: 916859 (The Pile)

Max Activating Token Index: 364

Text #7

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9867. Min Act: -0.0000

Data Index: 913609 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1688645 (The Pile)

Max Activating Token Index: 368

Text #9

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9379. Min Act: -0.0000

Data Index: 709906 (The Pile)

Max Activating Token Index: 632

Text #10

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1334065 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1915518 (The Pile)

Max Activating Token Index: 788

Text #12

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1311801 (The Pile)

Max Activating Token Index: 155

Text #13

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8860. Min Act: -0.0000

Data Index: 685018 (The Pile)

Max Activating Token Index: 630

Text #14

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8519. Min Act: -0.0000

Data Index: 1318119 (The Pile)

Max Activating Token Index: 18

Text #15

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1038707 (The Pile)

Max Activating Token Index: 441

Text #16

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9234. Min Act: -0.0000

Data Index: 1777490 (The Pile)

Max Activating Token Index: 155

Text #17

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8203. Min Act: -0.0000

Data Index: 524996 (The Pile)

Max Activating Token Index: 559

Text #18

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1159897 (The Pile)

Max Activating Token Index: 372

Text #19

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1197420 (The Pile)

Max Activating Token Index: 380