Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2773 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2775. Min Range: -1.2775

Max Act: 1.2042. Min Act: -0.0000

Data Index: 865525 (The Pile)

Max Activating Token Index: 437

Text #1

Max Range: 1.2775. Min Range: -1.2775

Max Act: 1.2775. Min Act: -0.0000

Data Index: 1507644 (The Pile)

Max Activating Token Index: 459

Text #2

Max Range: 1.2775. Min Range: -1.2775

Max Act: 1.0921. Min Act: -0.0000

Data Index: 771749 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 1.2775. Min Range: -1.2775

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1257908 (The Pile)

Max Activating Token Index: 605

Text #4

Max Range: 1.2775. Min Range: -1.2775

Max Act: 1.0000. Min Act: -0.0000

Data Index: 1988617 (The Pile)

Max Activating Token Index: 472

Text #5

Max Range: 1.2775. Min Range: -1.2775

Max Act: 0.9057. Min Act: -0.0000

Data Index: 345999 (The Pile)

Max Activating Token Index: 1006

Text #6

Max Range: 1.2775. Min Range: -1.2775

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1728531 (The Pile)

Max Activating Token Index: 268

Text #7

Max Range: 1.2775. Min Range: -1.2775

Max Act: 0.9823. Min Act: -0.0000

Data Index: 132423 (The Pile)

Max Activating Token Index: 970

Text #8

Max Range: 1.2775. Min Range: -1.2775

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1185576 (The Pile)

Max Activating Token Index: 926

Text #9

Max Range: 1.2775. Min Range: -1.2775

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1937325 (The Pile)

Max Activating Token Index: 179

Text #10

Max Range: 1.2775. Min Range: -1.2775

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1986041 (The Pile)

Max Activating Token Index: 193

Text #11

Max Range: 1.2775. Min Range: -1.2775

Max Act: 0.8300. Min Act: -0.0000

Data Index: 515406 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 1.2775. Min Range: -1.2775

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1456561 (The Pile)

Max Activating Token Index: 772

Text #13

Max Range: 1.2775. Min Range: -1.2775

Max Act: 0.7213. Min Act: -0.0000

Data Index: 336417 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 1.2775. Min Range: -1.2775

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1165914 (The Pile)

Max Activating Token Index: 1014

Text #15

Max Range: 1.2775. Min Range: -1.2775

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1834777 (The Pile)

Max Activating Token Index: 191

Text #16

Max Range: 1.2775. Min Range: -1.2775

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1127811 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 1.2775. Min Range: -1.2775

Max Act: 0.7030. Min Act: -0.0000

Data Index: 1307890 (The Pile)

Max Activating Token Index: 996

Text #18

Max Range: 1.2775. Min Range: -1.2775

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1313495 (The Pile)

Max Activating Token Index: 488

Text #19

Max Range: 1.2775. Min Range: -1.2775

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1569929 (The Pile)

Max Activating Token Index: 686