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

Dataset: The Pile

Neuron 333 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.7797. Min Act: -0.0000

Data Index: 933138 (The Pile)

Max Activating Token Index: 457

Text #1

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1748218 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.7441. Min Act: -0.0000

Data Index: 827402 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1779274 (The Pile)

Max Activating Token Index: 306

Text #4

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1773078 (The Pile)

Max Activating Token Index: 283

Text #5

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.7337. Min Act: -0.0000

Data Index: 464775 (The Pile)

Max Activating Token Index: 721

Text #6

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.7736. Min Act: -0.0000

Data Index: 1696822 (The Pile)

Max Activating Token Index: 500

Text #7

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1084323 (The Pile)

Max Activating Token Index: 122

Text #8

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.7557. Min Act: -0.0000

Data Index: 915951 (The Pile)

Max Activating Token Index: 302

Text #9

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1916993 (The Pile)

Max Activating Token Index: 564

Text #10

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.7100. Min Act: -0.0000

Data Index: 75575 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.5669. Min Act: -0.0000

Data Index: 749754 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.6364. Min Act: -0.0000

Data Index: 285983 (The Pile)

Max Activating Token Index: 83

Text #13

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1334322 (The Pile)

Max Activating Token Index: 683

Text #14

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.6211. Min Act: -0.0000

Data Index: 654804 (The Pile)

Max Activating Token Index: 253

Text #15

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1795735 (The Pile)

Max Activating Token Index: 471

Text #16

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1801044 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.6586. Min Act: -0.0000

Data Index: 215918 (The Pile)

Max Activating Token Index: 351

Text #18

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.7159. Min Act: -0.0000

Data Index: 850918 (The Pile)

Max Activating Token Index: 767

Text #19

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.6126. Min Act: -0.0000

Data Index: 826543 (The Pile)

Max Activating Token Index: 436