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

Dataset: The Pile

Neuron 309 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: 0.4178. Min Range: -0.4178

Max Act: 0.4178. Min Act: -0.0000

Data Index: 417548 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3744. Min Act: -0.0000

Data Index: 637683 (The Pile)

Max Activating Token Index: 553

Text #2

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3398. Min Act: -0.0000

Data Index: 69696 (The Pile)

Max Activating Token Index: 560

Text #3

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3569. Min Act: -0.0000

Data Index: 763375 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1868311 (The Pile)

Max Activating Token Index: 620

Text #5

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3400. Min Act: -0.0000

Data Index: 525152 (The Pile)

Max Activating Token Index: 405

Text #6

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3356. Min Act: -0.0000

Data Index: 359382 (The Pile)

Max Activating Token Index: 160

Text #7

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1939693 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1016624 (The Pile)

Max Activating Token Index: 663

Text #9

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.2958. Min Act: -0.0000

Data Index: 882704 (The Pile)

Max Activating Token Index: 211

Text #10

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.2958. Min Act: -0.0000

Data Index: 1848440 (The Pile)

Max Activating Token Index: 193

Text #11

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1598438 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3080. Min Act: -0.0000

Data Index: 758482 (The Pile)

Max Activating Token Index: 683

Text #13

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.2914. Min Act: -0.0000

Data Index: 776922 (The Pile)

Max Activating Token Index: 934

Text #14

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.2910. Min Act: -0.0000

Data Index: 1453719 (The Pile)

Max Activating Token Index: 554

Text #15

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3165. Min Act: -0.0000

Data Index: 597814 (The Pile)

Max Activating Token Index: 833

Text #16

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3040. Min Act: -0.0000

Data Index: 487281 (The Pile)

Max Activating Token Index: 776

Text #17

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.2860. Min Act: -0.0000

Data Index: 390477 (The Pile)

Max Activating Token Index: 400

Text #18

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.2597. Min Act: -0.0000

Data Index: 681291 (The Pile)

Max Activating Token Index: 826

Text #19

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.2739. Min Act: -0.0000

Data Index: 556838 (The Pile)

Max Activating Token Index: 228