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

Dataset: The Pile

Neuron 3639 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: 0.1301. Min Range: -0.1301

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1859288 (The Pile)

Max Activating Token Index: 819

Text #1

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1301. Min Act: -0.0000

Data Index: 1262850 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1092. Min Act: -0.0000

Data Index: 294941 (The Pile)

Max Activating Token Index: 257

Text #3

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1760789 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1993740 (The Pile)

Max Activating Token Index: 571

Text #5

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1018. Min Act: -0.0000

Data Index: 193473 (The Pile)

Max Activating Token Index: 639

Text #6

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1075027 (The Pile)

Max Activating Token Index: 587

Text #7

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0974. Min Act: -0.0000

Data Index: 819890 (The Pile)

Max Activating Token Index: 913

Text #8

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0960. Min Act: -0.0000

Data Index: 1455068 (The Pile)

Max Activating Token Index: 239

Text #9

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0898. Min Act: -0.0000

Data Index: 1649098 (The Pile)

Max Activating Token Index: 643

Text #10

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1855985 (The Pile)

Max Activating Token Index: 888

Text #11

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0884. Min Act: -0.0000

Data Index: 957605 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0990. Min Act: -0.0000

Data Index: 99891 (The Pile)

Max Activating Token Index: 825

Text #13

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0856. Min Act: -0.0000

Data Index: 8357 (The Pile)

Max Activating Token Index: 403

Text #14

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0870. Min Act: -0.0000

Data Index: 750578 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1742376 (The Pile)

Max Activating Token Index: 420

Text #16

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0814. Min Act: -0.0000

Data Index: 449105 (The Pile)

Max Activating Token Index: 497

Text #17

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0813. Min Act: -0.0000

Data Index: 887540 (The Pile)

Max Activating Token Index: 607

Text #18

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0831. Min Act: -0.0000

Data Index: 122448 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0824. Min Act: -0.0000

Data Index: 18472 (The Pile)

Max Activating Token Index: 315