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

Dataset: The Pile

Neuron 372 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0381. Min Range: -1.0381

Max Act: 1.0381. Min Act: -0.0000

Data Index: 390084 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 1.0381. Min Range: -1.0381

Max Act: 1.0137. Min Act: -0.0000

Data Index: 1384945 (The Pile)

Max Activating Token Index: 306

Text #2

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.9900. Min Act: -0.0000

Data Index: 693718 (The Pile)

Max Activating Token Index: 493

Text #3

Max Range: 1.0381. Min Range: -1.0381

Max Act: 1.0249. Min Act: -0.0000

Data Index: 596368 (The Pile)

Max Activating Token Index: 136

Text #4

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1638620 (The Pile)

Max Activating Token Index: 335

Text #5

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.8634. Min Act: -0.0000

Data Index: 317326 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.8113. Min Act: -0.0000

Data Index: 627775 (The Pile)

Max Activating Token Index: 991

Text #7

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.8064. Min Act: -0.0000

Data Index: 761280 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.7066. Min Act: -0.0000

Data Index: 565786 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.7833. Min Act: -0.0000

Data Index: 123402 (The Pile)

Max Activating Token Index: 472

Text #10

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.8056. Min Act: -0.0000

Data Index: 1538172 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.7342. Min Act: -0.0000

Data Index: 872167 (The Pile)

Max Activating Token Index: 279

Text #12

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.8021. Min Act: -0.0000

Data Index: 647154 (The Pile)

Max Activating Token Index: 945

Text #13

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.6112. Min Act: -0.0000

Data Index: 787468 (The Pile)

Max Activating Token Index: 1018

Text #14

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1378212 (The Pile)

Max Activating Token Index: 257

Text #15

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.7022. Min Act: -0.0000

Data Index: 133352 (The Pile)

Max Activating Token Index: 325

Text #16

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1850226 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.5779. Min Act: -0.0000

Data Index: 292938 (The Pile)

Max Activating Token Index: 79

Text #18

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1867355 (The Pile)

Max Activating Token Index: 436

Text #19

Max Range: 1.0381. Min Range: -1.0381

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1658279 (The Pile)

Max Activating Token Index: 69