Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 709 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.9310. Min Act: -0.0000

Data Index: 896114 (The Pile)

Max Activating Token Index: 298

Text #1

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1791956 (The Pile)

Max Activating Token Index: 884

Text #2

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7128. Min Act: -0.0000

Data Index: 352800 (The Pile)

Max Activating Token Index: 255

Text #3

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6711. Min Act: -0.0000

Data Index: 867596 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7045. Min Act: -0.0000

Data Index: 1982953 (The Pile)

Max Activating Token Index: 464

Text #5

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6958. Min Act: -0.0000

Data Index: 577472 (The Pile)

Max Activating Token Index: 849

Text #6

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6035. Min Act: -0.0000

Data Index: 731340 (The Pile)

Max Activating Token Index: 898

Text #7

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1655058 (The Pile)

Max Activating Token Index: 320

Text #8

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1035407 (The Pile)

Max Activating Token Index: 384

Text #9

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6289. Min Act: -0.0000

Data Index: 1747313 (The Pile)

Max Activating Token Index: 911

Text #10

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6005. Min Act: -0.0000

Data Index: 985806 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6364. Min Act: -0.0000

Data Index: 71510 (The Pile)

Max Activating Token Index: 524

Text #12

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1372172 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1914842 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.5992. Min Act: -0.0000

Data Index: 18722 (The Pile)

Max Activating Token Index: 837

Text #15

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1672880 (The Pile)

Max Activating Token Index: 408

Text #16

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.5823. Min Act: -0.0000

Data Index: 853035 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6398. Min Act: -0.0000

Data Index: 29245 (The Pile)

Max Activating Token Index: 468

Text #18

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.5855. Min Act: -0.0000

Data Index: 90424 (The Pile)

Max Activating Token Index: 609

Text #19

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6068. Min Act: -0.0000

Data Index: 130463 (The Pile)

Max Activating Token Index: 416