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

Dataset: The Pile

Neuron 1960 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1358. Min Range: -5.1358

Max Act: 5.1358. Min Act: -0.0000

Data Index: 1438297 (The Pile)

Max Activating Token Index: 369

Text #1

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.8938. Min Act: -0.0000

Data Index: 1680455 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.9778. Min Act: -0.0000

Data Index: 1719134 (The Pile)

Max Activating Token Index: 202

Text #3

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.9411. Min Act: -0.0000

Data Index: 343001 (The Pile)

Max Activating Token Index: 384

Text #4

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.5400. Min Act: -0.0000

Data Index: 1523817 (The Pile)

Max Activating Token Index: 503

Text #5

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.4779. Min Act: -0.0000

Data Index: 1908398 (The Pile)

Max Activating Token Index: 586

Text #6

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.1591. Min Act: -0.0000

Data Index: 917295 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.1490. Min Act: -0.0000

Data Index: 1954444 (The Pile)

Max Activating Token Index: 336

Text #8

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.2204. Min Act: -0.0000

Data Index: 870220 (The Pile)

Max Activating Token Index: 687

Text #9

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.3153. Min Act: -0.0000

Data Index: 668481 (The Pile)

Max Activating Token Index: 876

Text #10

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.3835. Min Act: -0.0000

Data Index: 1782803 (The Pile)

Max Activating Token Index: 922

Text #11

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.0565. Min Act: -0.0000

Data Index: 970518 (The Pile)

Max Activating Token Index: 468

Text #12

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.0328. Min Act: -0.0000

Data Index: 1310717 (The Pile)

Max Activating Token Index: 78

Text #13

Max Range: 5.1358. Min Range: -5.1358

Max Act: 4.1618. Min Act: -0.0000

Data Index: 1402728 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 5.1358. Min Range: -5.1358

Max Act: 3.9735. Min Act: -0.0000

Data Index: 485612 (The Pile)

Max Activating Token Index: 960

Text #15

Max Range: 5.1358. Min Range: -5.1358

Max Act: 3.9188. Min Act: -0.0000

Data Index: 1689284 (The Pile)

Max Activating Token Index: 209

Text #16

Max Range: 5.1358. Min Range: -5.1358

Max Act: 3.9027. Min Act: -0.0000

Data Index: 599197 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 5.1358. Min Range: -5.1358

Max Act: 3.8868. Min Act: -0.0000

Data Index: 4522 (The Pile)

Max Activating Token Index: 214

Text #18

Max Range: 5.1358. Min Range: -5.1358

Max Act: 3.8723. Min Act: -0.0000

Data Index: 247913 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 5.1358. Min Range: -5.1358

Max Act: 3.3815. Min Act: -0.0000

Data Index: 1107434 (The Pile)

Max Activating Token Index: 573