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

Dataset: The Pile

Neuron 4615 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5764. Min Range: -5.5764

Max Act: 5.5764. Min Act: -0.0000

Data Index: 936102 (The Pile)

Max Activating Token Index: 263

Text #1

Max Range: 5.5764. Min Range: -5.5764

Max Act: 5.3895. Min Act: -0.0000

Data Index: 1494529 (The Pile)

Max Activating Token Index: 66

Text #2

Max Range: 5.5764. Min Range: -5.5764

Max Act: 4.2850. Min Act: -0.0000

Data Index: 1149980 (The Pile)

Max Activating Token Index: 549

Text #3

Max Range: 5.5764. Min Range: -5.5764

Max Act: 3.4708. Min Act: -0.0000

Data Index: 487780 (The Pile)

Max Activating Token Index: 324

Text #4

Max Range: 5.5764. Min Range: -5.5764

Max Act: 2.8034. Min Act: -0.0000

Data Index: 1834836 (The Pile)

Max Activating Token Index: 912

Text #5

Max Range: 5.5764. Min Range: -5.5764

Max Act: 2.6946. Min Act: -0.0000

Data Index: 1169784 (The Pile)

Max Activating Token Index: 95

Text #6

Max Range: 5.5764. Min Range: -5.5764

Max Act: 2.8548. Min Act: -0.0000

Data Index: 707079 (The Pile)

Max Activating Token Index: 884

Text #7

Max Range: 5.5764. Min Range: -5.5764

Max Act: 2.6496. Min Act: -0.0000

Data Index: 858431 (The Pile)

Max Activating Token Index: 227

Text #8

Max Range: 5.5764. Min Range: -5.5764

Max Act: 2.4602. Min Act: -0.0000

Data Index: 1087920 (The Pile)

Max Activating Token Index: 690

Text #9

Max Range: 5.5764. Min Range: -5.5764

Max Act: 2.4529. Min Act: -0.0000

Data Index: 1616634 (The Pile)

Max Activating Token Index: 585

Text #10

Max Range: 5.5764. Min Range: -5.5764

Max Act: 2.6075. Min Act: -0.0000

Data Index: 1759169 (The Pile)

Max Activating Token Index: 495

Text #11

Max Range: 5.5764. Min Range: -5.5764

Max Act: 2.4131. Min Act: -0.0000

Data Index: 1178553 (The Pile)

Max Activating Token Index: 287

Text #12

Max Range: 5.5764. Min Range: -5.5764

Max Act: 2.4078. Min Act: -0.0000

Data Index: 1999082 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 5.5764. Min Range: -5.5764

Max Act: 2.4102. Min Act: -0.0000

Data Index: 482183 (The Pile)

Max Activating Token Index: 315

Text #14

Max Range: 5.5764. Min Range: -5.5764

Max Act: 2.2586. Min Act: -0.0000

Data Index: 144139 (The Pile)

Max Activating Token Index: 432

Text #15

Max Range: 5.5764. Min Range: -5.5764

Max Act: 2.2442. Min Act: -0.0000

Data Index: 280249 (The Pile)

Max Activating Token Index: 535

Text #16

Max Range: 5.5764. Min Range: -5.5764

Max Act: 2.2988. Min Act: -0.0000

Data Index: 1865904 (The Pile)

Max Activating Token Index: 994

Text #17

Max Range: 5.5764. Min Range: -5.5764

Max Act: 2.0700. Min Act: -0.0000

Data Index: 663658 (The Pile)

Max Activating Token Index: 352

Text #18

Max Range: 5.5764. Min Range: -5.5764

Max Act: 1.9694. Min Act: -0.0000

Data Index: 1403852 (The Pile)

Max Activating Token Index: 444

Text #19

Max Range: 5.5764. Min Range: -5.5764

Max Act: 2.1018. Min Act: -0.0000

Data Index: 506318 (The Pile)

Max Activating Token Index: 614