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

Dataset: The Pile

Neuron 4861 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: 1.3323. Min Range: -1.3323

Max Act: 1.3323. Min Act: -0.0000

Data Index: 709430 (The Pile)

Max Activating Token Index: 755

Text #1

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.1307. Min Act: -0.0000

Data Index: 234650 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1450320 (The Pile)

Max Activating Token Index: 76

Text #3

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.9905. Min Act: -0.0000

Data Index: 930941 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.8507. Min Act: -0.0000

Data Index: 149670 (The Pile)

Max Activating Token Index: 435

Text #5

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1963617 (The Pile)

Max Activating Token Index: 424

Text #6

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.8234. Min Act: -0.0000

Data Index: 422961 (The Pile)

Max Activating Token Index: 406

Text #7

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.7895. Min Act: -0.0000

Data Index: 353190 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.8030. Min Act: -0.0000

Data Index: 990978 (The Pile)

Max Activating Token Index: 781

Text #9

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1610862 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.8031. Min Act: -0.0000

Data Index: 75688 (The Pile)

Max Activating Token Index: 692

Text #11

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.7762. Min Act: -0.0000

Data Index: 225771 (The Pile)

Max Activating Token Index: 946

Text #12

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1091423 (The Pile)

Max Activating Token Index: 269

Text #13

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.7503. Min Act: -0.0000

Data Index: 387589 (The Pile)

Max Activating Token Index: 965

Text #14

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.7802. Min Act: -0.0000

Data Index: 953934 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.7980. Min Act: -0.0000

Data Index: 1082062 (The Pile)

Max Activating Token Index: 467

Text #16

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.7372. Min Act: -0.0000

Data Index: 493358 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.8021. Min Act: -0.0000

Data Index: 228562 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.7555. Min Act: -0.0000

Data Index: 12980 (The Pile)

Max Activating Token Index: 346

Text #19

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1308896 (The Pile)

Max Activating Token Index: 586