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

Dataset: The Pile

Neuron 751 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: 0.4151. Min Range: -0.4151

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1185162 (The Pile)

Max Activating Token Index: 490

Text #1

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3696. Min Act: -0.0000

Data Index: 269461 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1420453 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1960934 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3244. Min Act: -0.0000

Data Index: 1481158 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1509521 (The Pile)

Max Activating Token Index: 624

Text #6

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1276455 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2776. Min Act: -0.0000

Data Index: 410772 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2846. Min Act: -0.0000

Data Index: 262635 (The Pile)

Max Activating Token Index: 631

Text #9

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2866. Min Act: -0.0000

Data Index: 575996 (The Pile)

Max Activating Token Index: 329

Text #10

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2760. Min Act: -0.0000

Data Index: 3410 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1004706 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2781. Min Act: -0.0000

Data Index: 287575 (The Pile)

Max Activating Token Index: 606

Text #13

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2598. Min Act: -0.0000

Data Index: 346124 (The Pile)

Max Activating Token Index: 732

Text #14

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2767. Min Act: -0.0000

Data Index: 938238 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2706. Min Act: -0.0000

Data Index: 136230 (The Pile)

Max Activating Token Index: 65

Text #16

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2672. Min Act: -0.0000

Data Index: 422908 (The Pile)

Max Activating Token Index: 777

Text #17

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2333. Min Act: -0.0000

Data Index: 18158 (The Pile)

Max Activating Token Index: 631

Text #18

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2675. Min Act: -0.0000

Data Index: 852981 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1511142 (The Pile)

Max Activating Token Index: 882