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

Dataset: The Pile

Neuron 1781 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: 0.8252. Min Range: -0.8252

Max Act: 0.8167. Min Act: -0.0000

Data Index: 913169 (The Pile)

Max Activating Token Index: 654

Text #1

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1149905 (The Pile)

Max Activating Token Index: 922

Text #2

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7397. Min Act: -0.0000

Data Index: 760857 (The Pile)

Max Activating Token Index: 928

Text #3

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7426. Min Act: -0.0000

Data Index: 631014 (The Pile)

Max Activating Token Index: 38

Text #4

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6846. Min Act: -0.0000

Data Index: 100178 (The Pile)

Max Activating Token Index: 722

Text #5

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7420. Min Act: -0.0000

Data Index: 753580 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7079. Min Act: -0.0000

Data Index: 1661672 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1765247 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6679. Min Act: 0.0000

Data Index: 1557821 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6786. Min Act: -0.0000

Data Index: 905283 (The Pile)

Max Activating Token Index: 199

Text #10

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6408. Min Act: -0.0000

Data Index: 295356 (The Pile)

Max Activating Token Index: 640

Text #11

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1927710 (The Pile)

Max Activating Token Index: 694

Text #12

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6241. Min Act: -0.0000

Data Index: 985676 (The Pile)

Max Activating Token Index: 310

Text #13

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1978434 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1083002 (The Pile)

Max Activating Token Index: 185

Text #15

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6307. Min Act: -0.0000

Data Index: 396770 (The Pile)

Max Activating Token Index: 767

Text #16

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1072373 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1572464 (The Pile)

Max Activating Token Index: 486

Text #18

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5744. Min Act: -0.0000

Data Index: 374147 (The Pile)

Max Activating Token Index: 392

Text #19

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1571349 (The Pile)

Max Activating Token Index: 55