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

Dataset: The Pile

Neuron 658 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: 3.6130. Min Range: -3.6130

Max Act: 3.6130. Min Act: -0.0000

Data Index: 1766840 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.4859. Min Act: -0.0000

Data Index: 1577331 (The Pile)

Max Activating Token Index: 562

Text #2

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.3516. Min Act: -0.0000

Data Index: 446434 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 3.6130. Min Range: -3.6130

Max Act: 2.8614. Min Act: -0.0000

Data Index: 193791 (The Pile)

Max Activating Token Index: 447

Text #4

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.3259. Min Act: -0.0000

Data Index: 1935881 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.1102. Min Act: -0.0000

Data Index: 1317348 (The Pile)

Max Activating Token Index: 463

Text #6

Max Range: 3.6130. Min Range: -3.6130

Max Act: 2.7266. Min Act: -0.0000

Data Index: 1928637 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.1896. Min Act: -0.0000

Data Index: 1917389 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 3.6130. Min Range: -3.6130

Max Act: 2.7232. Min Act: -0.0000

Data Index: 1347531 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.0905. Min Act: -0.0000

Data Index: 1357288 (The Pile)

Max Activating Token Index: 135

Text #10

Max Range: 3.6130. Min Range: -3.6130

Max Act: 2.5241. Min Act: -0.0000

Data Index: 730275 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 3.6130. Min Range: -3.6130

Max Act: 2.7544. Min Act: -0.0000

Data Index: 1490055 (The Pile)

Max Activating Token Index: 327

Text #12

Max Range: 3.6130. Min Range: -3.6130

Max Act: 2.9815. Min Act: -0.0000

Data Index: 895560 (The Pile)

Max Activating Token Index: 612

Text #13

Max Range: 3.6130. Min Range: -3.6130

Max Act: 2.8414. Min Act: -0.0000

Data Index: 1155748 (The Pile)

Max Activating Token Index: 455

Text #14

Max Range: 3.6130. Min Range: -3.6130

Max Act: 2.8131. Min Act: -0.0000

Data Index: 1250383 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 3.6130. Min Range: -3.6130

Max Act: 2.9336. Min Act: -0.0000

Data Index: 276819 (The Pile)

Max Activating Token Index: 560

Text #16

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.0838. Min Act: -0.0000

Data Index: 1373852 (The Pile)

Max Activating Token Index: 943

Text #17

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.1218. Min Act: -0.0000

Data Index: 1607666 (The Pile)

Max Activating Token Index: 659

Text #18

Max Range: 3.6130. Min Range: -3.6130

Max Act: 2.9399. Min Act: -0.0000

Data Index: 150015 (The Pile)

Max Activating Token Index: 245

Text #19

Max Range: 3.6130. Min Range: -3.6130

Max Act: 2.7744. Min Act: -0.0000

Data Index: 726314 (The Pile)

Max Activating Token Index: 3