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

Dataset: The Pile

Neuron 3411 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.8482. Min Act: -0.0000

Data Index: 1008698 (The Pile)

Max Activating Token Index: 966

Text #1

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.8319. Min Act: -0.0000

Data Index: 238497 (The Pile)

Max Activating Token Index: 833

Text #2

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6393. Min Act: -0.0000

Data Index: 699831 (The Pile)

Max Activating Token Index: 777

Text #3

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7655. Min Act: -0.0000

Data Index: 205505 (The Pile)

Max Activating Token Index: 373

Text #4

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.8210. Min Act: -0.0000

Data Index: 1209604 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6920. Min Act: -0.0000

Data Index: 1268207 (The Pile)

Max Activating Token Index: 323

Text #6

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6111. Min Act: -0.0000

Data Index: 419485 (The Pile)

Max Activating Token Index: 829

Text #7

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6841. Min Act: -0.0000

Data Index: 1164893 (The Pile)

Max Activating Token Index: 484

Text #8

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.4150. Min Act: -0.0000

Data Index: 1446218 (The Pile)

Max Activating Token Index: 598

Text #9

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7613. Min Act: -0.0000

Data Index: 787070 (The Pile)

Max Activating Token Index: 673

Text #10

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6344. Min Act: -0.0000

Data Index: 1089063 (The Pile)

Max Activating Token Index: 185

Text #11

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6823. Min Act: -0.0000

Data Index: 294328 (The Pile)

Max Activating Token Index: 522

Text #12

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6384. Min Act: -0.0000

Data Index: 833812 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6460. Min Act: -0.0000

Data Index: 265512 (The Pile)

Max Activating Token Index: 548

Text #14

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.4350. Min Act: -0.0000

Data Index: 1331343 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.5514. Min Act: -0.0000

Data Index: 315488 (The Pile)

Max Activating Token Index: 820

Text #16

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.5447. Min Act: -0.0000

Data Index: 1072704 (The Pile)

Max Activating Token Index: 583

Text #17

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6084. Min Act: -0.0000

Data Index: 22221 (The Pile)

Max Activating Token Index: 945

Text #18

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.5257. Min Act: -0.0000

Data Index: 1815122 (The Pile)

Max Activating Token Index: 478

Text #19

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.4183. Min Act: -0.0000

Data Index: 741756 (The Pile)

Max Activating Token Index: 551