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

Dataset: The Pile

Neuron 1947 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: 1.0353. Min Range: -1.0353

Max Act: 1.0353. Min Act: -0.0000

Data Index: 631629 (The Pile)

Max Activating Token Index: 312

Text #1

Max Range: 1.0353. Min Range: -1.0353

Max Act: 1.0337. Min Act: -0.0000

Data Index: 454051 (The Pile)

Max Activating Token Index: 214

Text #2

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.9612. Min Act: -0.0000

Data Index: 886020 (The Pile)

Max Activating Token Index: 624

Text #3

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.9247. Min Act: -0.0000

Data Index: 932459 (The Pile)

Max Activating Token Index: 315

Text #4

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.8690. Min Act: -0.0000

Data Index: 393239 (The Pile)

Max Activating Token Index: 356

Text #5

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.8394. Min Act: -0.0000

Data Index: 469742 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.8394. Min Act: -0.0000

Data Index: 562648 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1836194 (The Pile)

Max Activating Token Index: 73

Text #8

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1123194 (The Pile)

Max Activating Token Index: 450

Text #9

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7266. Min Act: -0.0000

Data Index: 470306 (The Pile)

Max Activating Token Index: 589

Text #10

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.6741. Min Act: -0.0000

Data Index: 930131 (The Pile)

Max Activating Token Index: 841

Text #11

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1088516 (The Pile)

Max Activating Token Index: 708

Text #12

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7983. Min Act: -0.0000

Data Index: 714853 (The Pile)

Max Activating Token Index: 84

Text #13

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1099276 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.6786. Min Act: -0.0000

Data Index: 374032 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1806143 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7037. Min Act: -0.0000

Data Index: 613507 (The Pile)

Max Activating Token Index: 888

Text #17

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7164. Min Act: -0.0000

Data Index: 342082 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.6556. Min Act: -0.0000

Data Index: 1570905 (The Pile)

Max Activating Token Index: 38

Text #19

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1574441 (The Pile)

Max Activating Token Index: 591