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

Dataset: The Pile

Neuron 3688 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: 1.1580. Min Range: -1.1580

Max Act: 1.1580. Min Act: -0.0000

Data Index: 506759 (The Pile)

Max Activating Token Index: 514

Text #1

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.1042. Min Act: -0.0000

Data Index: 1433612 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1195068 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7306. Min Act: -0.0000

Data Index: 348386 (The Pile)

Max Activating Token Index: 938

Text #4

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8829. Min Act: -0.0000

Data Index: 203860 (The Pile)

Max Activating Token Index: 372

Text #5

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9951. Min Act: -0.0000

Data Index: 506467 (The Pile)

Max Activating Token Index: 398

Text #6

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1881545 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9118. Min Act: -0.0000

Data Index: 706027 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8046. Min Act: -0.0000

Data Index: 788901 (The Pile)

Max Activating Token Index: 849

Text #9

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8036. Min Act: -0.0000

Data Index: 155454 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9275. Min Act: -0.0000

Data Index: 544033 (The Pile)

Max Activating Token Index: 37

Text #11

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8239. Min Act: -0.0000

Data Index: 264839 (The Pile)

Max Activating Token Index: 75

Text #12

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1098176 (The Pile)

Max Activating Token Index: 405

Text #13

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8247. Min Act: -0.0000

Data Index: 1396213 (The Pile)

Max Activating Token Index: 288

Text #14

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8881. Min Act: -0.0000

Data Index: 734746 (The Pile)

Max Activating Token Index: 582

Text #15

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1427867 (The Pile)

Max Activating Token Index: 605

Text #16

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8217. Min Act: -0.0000

Data Index: 118321 (The Pile)

Max Activating Token Index: 665

Text #17

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8750. Min Act: -0.0000

Data Index: 674240 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7550. Min Act: -0.0000

Data Index: 411910 (The Pile)

Max Activating Token Index: 731

Text #19

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7780. Min Act: -0.0000

Data Index: 1913702 (The Pile)

Max Activating Token Index: 547