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

Dataset: The Pile

Neuron 3421 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: 1.0885. Min Range: -1.0885

Max Act: 1.0885. Min Act: -0.0000

Data Index: 470546 (The Pile)

Max Activating Token Index: 729

Text #1

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.9878. Min Act: -0.0000

Data Index: 958173 (The Pile)

Max Activating Token Index: 482

Text #2

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.9597. Min Act: -0.0000

Data Index: 1751040 (The Pile)

Max Activating Token Index: 272

Text #3

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.9019. Min Act: -0.0000

Data Index: 1111412 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.9430. Min Act: 0.0000

Data Index: 732142 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.9604. Min Act: 0.0000

Data Index: 1405259 (The Pile)

Max Activating Token Index: 486

Text #6

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.9432. Min Act: -0.0000

Data Index: 290032 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1534849 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.8778. Min Act: -0.0000

Data Index: 491575 (The Pile)

Max Activating Token Index: 431

Text #9

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1232919 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.8302. Min Act: -0.0000

Data Index: 603478 (The Pile)

Max Activating Token Index: 37

Text #11

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1172748 (The Pile)

Max Activating Token Index: 703

Text #12

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.8178. Min Act: 0.0000

Data Index: 1237080 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.7647. Min Act: 0.0000

Data Index: 30767 (The Pile)

Max Activating Token Index: 308

Text #14

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.8111. Min Act: -0.0000

Data Index: 717023 (The Pile)

Max Activating Token Index: 357

Text #15

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.8107. Min Act: -0.0000

Data Index: 321154 (The Pile)

Max Activating Token Index: 391

Text #16

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.7735. Min Act: -0.0000

Data Index: 524304 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.7993. Min Act: 0.0000

Data Index: 1972716 (The Pile)

Max Activating Token Index: 565

Text #18

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1910616 (The Pile)

Max Activating Token Index: 335

Text #19

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1167072 (The Pile)

Max Activating Token Index: 678