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

Dataset: The Pile

Neuron 3376 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1449477 (The Pile)

Max Activating Token Index: 442

Text #1

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6086. Min Act: -0.0000

Data Index: 785825 (The Pile)

Max Activating Token Index: 609

Text #2

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6102. Min Act: -0.0000

Data Index: 421282 (The Pile)

Max Activating Token Index: 347

Text #3

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5625. Min Act: -0.0000

Data Index: 873668 (The Pile)

Max Activating Token Index: 692

Text #4

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1217033 (The Pile)

Max Activating Token Index: 343

Text #5

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6195. Min Act: -0.0000

Data Index: 775452 (The Pile)

Max Activating Token Index: 797

Text #6

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5653. Min Act: -0.0000

Data Index: 164534 (The Pile)

Max Activating Token Index: 856

Text #7

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5631. Min Act: -0.0000

Data Index: 56355 (The Pile)

Max Activating Token Index: 635

Text #8

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1957500 (The Pile)

Max Activating Token Index: 489

Text #9

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5691. Min Act: -0.0000

Data Index: 680803 (The Pile)

Max Activating Token Index: 243

Text #10

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5580. Min Act: -0.0000

Data Index: 489517 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5315. Min Act: -0.0000

Data Index: 257192 (The Pile)

Max Activating Token Index: 66

Text #12

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1609014 (The Pile)

Max Activating Token Index: 247

Text #13

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1226851 (The Pile)

Max Activating Token Index: 961

Text #14

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1508018 (The Pile)

Max Activating Token Index: 915

Text #15

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1844308 (The Pile)

Max Activating Token Index: 881

Text #16

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5498. Min Act: -0.0000

Data Index: 436350 (The Pile)

Max Activating Token Index: 927

Text #17

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1627716 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5651. Min Act: -0.0000

Data Index: 150738 (The Pile)

Max Activating Token Index: 925

Text #19

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.4710. Min Act: -0.0000

Data Index: 736434 (The Pile)

Max Activating Token Index: 840