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

Dataset: The Pile

Neuron 2517 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.5508. Min Act: -0.0000

Data Index: 1724103 (The Pile)

Max Activating Token Index: 759

Text #1

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.5774. Min Act: -0.0000

Data Index: 1329914 (The Pile)

Max Activating Token Index: 561

Text #2

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.3781. Min Act: -0.0000

Data Index: 703339 (The Pile)

Max Activating Token Index: 459

Text #3

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.2593. Min Act: -0.0000

Data Index: 1900842 (The Pile)

Max Activating Token Index: 868

Text #4

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.2732. Min Act: -0.0000

Data Index: 1120620 (The Pile)

Max Activating Token Index: 349

Text #5

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.2164. Min Act: -0.0000

Data Index: 1831883 (The Pile)

Max Activating Token Index: 521

Text #6

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.1712. Min Act: -0.0000

Data Index: 255201 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.0983. Min Act: -0.0000

Data Index: 166270 (The Pile)

Max Activating Token Index: 803

Text #8

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.0838. Min Act: -0.0000

Data Index: 756812 (The Pile)

Max Activating Token Index: 410

Text #9

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.1336. Min Act: -0.0000

Data Index: 884307 (The Pile)

Max Activating Token Index: 578

Text #10

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.0888. Min Act: -0.0000

Data Index: 1686401 (The Pile)

Max Activating Token Index: 321

Text #11

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.1846. Min Act: -0.0000

Data Index: 1015224 (The Pile)

Max Activating Token Index: 548

Text #12

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.0891. Min Act: -0.0000

Data Index: 100604 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.0837. Min Act: -0.0000

Data Index: 236510 (The Pile)

Max Activating Token Index: 191

Text #14

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.0824. Min Act: -0.0000

Data Index: 1098651 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.0367. Min Act: -0.0000

Data Index: 1659648 (The Pile)

Max Activating Token Index: 310

Text #16

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.0220. Min Act: -0.0000

Data Index: 1501476 (The Pile)

Max Activating Token Index: 241

Text #17

Max Range: 1.5774. Min Range: -1.5774

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1309368 (The Pile)

Max Activating Token Index: 84

Text #18

Max Range: 1.5774. Min Range: -1.5774

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1466206 (The Pile)

Max Activating Token Index: 162

Text #19

Max Range: 1.5774. Min Range: -1.5774

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1061711 (The Pile)

Max Activating Token Index: 291