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

Dataset: The Pile

Neuron 3511 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3480. Min Act: -0.0000

Data Index: 908001 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1811469 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1175425 (The Pile)

Max Activating Token Index: 782

Text #3

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1547799 (The Pile)

Max Activating Token Index: 663

Text #4

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3925. Min Act: -0.0000

Data Index: 124288 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3641. Min Act: -0.0000

Data Index: 473310 (The Pile)

Max Activating Token Index: 497

Text #6

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1075647 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1249567 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3627. Min Act: -0.0000

Data Index: 1125177 (The Pile)

Max Activating Token Index: 902

Text #9

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3687. Min Act: -0.0000

Data Index: 763322 (The Pile)

Max Activating Token Index: 663

Text #10

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3506. Min Act: -0.0000

Data Index: 42067 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3205. Min Act: -0.0000

Data Index: 114874 (The Pile)

Max Activating Token Index: 543

Text #12

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3803. Min Act: -0.0000

Data Index: 367761 (The Pile)

Max Activating Token Index: 43

Text #13

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1413859 (The Pile)

Max Activating Token Index: 849

Text #14

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3608. Min Act: -0.0000

Data Index: 857464 (The Pile)

Max Activating Token Index: 722

Text #15

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3751. Min Act: -0.0000

Data Index: 340529 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3599. Min Act: -0.0000

Data Index: 675353 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3806. Min Act: -0.0000

Data Index: 37220 (The Pile)

Max Activating Token Index: 583

Text #18

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1278857 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3415. Min Act: -0.0000

Data Index: 489149 (The Pile)

Max Activating Token Index: 823