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

Dataset: The Pile

Neuron 3503 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.8850. Min Act: -0.0000

Data Index: 608279 (The Pile)

Max Activating Token Index: 714

Text #1

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4701. Min Act: -0.0000

Data Index: 1038229 (The Pile)

Max Activating Token Index: 559

Text #2

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4102. Min Act: -0.0000

Data Index: 1052651 (The Pile)

Max Activating Token Index: 729

Text #3

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4924. Min Act: -0.0000

Data Index: 1514556 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.3426. Min Act: -0.0000

Data Index: 615036 (The Pile)

Max Activating Token Index: 964

Text #5

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.3068. Min Act: -0.0000

Data Index: 1533866 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.1413. Min Act: -0.0000

Data Index: 1406628 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.3854. Min Act: 0.0000

Data Index: 991910 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.1140. Min Act: -0.0000

Data Index: 607020 (The Pile)

Max Activating Token Index: 576

Text #9

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4069. Min Act: -0.0000

Data Index: 570223 (The Pile)

Max Activating Token Index: 854

Text #10

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.2094. Min Act: -0.0000

Data Index: 994295 (The Pile)

Max Activating Token Index: 886

Text #11

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.0898. Min Act: -0.0000

Data Index: 461858 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.2177. Min Act: -0.0000

Data Index: 1275464 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.0717. Min Act: -0.0000

Data Index: 886806 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 1.8850. Min Range: -1.8850

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1415180 (The Pile)

Max Activating Token Index: 202

Text #15

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1344484 (The Pile)

Max Activating Token Index: 474

Text #16

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.0232. Min Act: -0.0000

Data Index: 533128 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.1424. Min Act: -0.0000

Data Index: 1829780 (The Pile)

Max Activating Token Index: 293

Text #18

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.1428. Min Act: 0.0000

Data Index: 634275 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.0716. Min Act: 0.0000

Data Index: 1659285 (The Pile)

Max Activating Token Index: 540