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

Dataset: The Pile

Neuron 4087 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9904. Min Range: -1.9904

Max Act: 1.9904. Min Act: -0.0000

Data Index: 1658909 (The Pile)

Max Activating Token Index: 974

Text #1

Max Range: 1.9904. Min Range: -1.9904

Max Act: 1.4291. Min Act: -0.0000

Data Index: 1877536 (The Pile)

Max Activating Token Index: 424

Text #2

Max Range: 1.9904. Min Range: -1.9904

Max Act: 1.2973. Min Act: -0.0000

Data Index: 20900 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 1.9904. Min Range: -1.9904

Max Act: 1.3647. Min Act: -0.0000

Data Index: 1728626 (The Pile)

Max Activating Token Index: 794

Text #4

Max Range: 1.9904. Min Range: -1.9904

Max Act: 1.2928. Min Act: -0.0000

Data Index: 1295930 (The Pile)

Max Activating Token Index: 190

Text #5

Max Range: 1.9904. Min Range: -1.9904

Max Act: 1.0664. Min Act: -0.0000

Data Index: 294044 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 1.9904. Min Range: -1.9904

Max Act: 1.1386. Min Act: -0.0000

Data Index: 212300 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 1.9904. Min Range: -1.9904

Max Act: 1.1477. Min Act: -0.0000

Data Index: 1183238 (The Pile)

Max Activating Token Index: 689

Text #8

Max Range: 1.9904. Min Range: -1.9904

Max Act: 0.9881. Min Act: -0.0000

Data Index: 930949 (The Pile)

Max Activating Token Index: 826

Text #9

Max Range: 1.9904. Min Range: -1.9904

Max Act: 1.2015. Min Act: -0.0000

Data Index: 1517156 (The Pile)

Max Activating Token Index: 434

Text #10

Max Range: 1.9904. Min Range: -1.9904

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1492711 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 1.9904. Min Range: -1.9904

Max Act: 0.8746. Min Act: -0.0000

Data Index: 182749 (The Pile)

Max Activating Token Index: 439

Text #12

Max Range: 1.9904. Min Range: -1.9904

Max Act: 0.6620. Min Act: -0.0000

Data Index: 470461 (The Pile)

Max Activating Token Index: 300

Text #13

Max Range: 1.9904. Min Range: -1.9904

Max Act: 0.9640. Min Act: -0.0000

Data Index: 239428 (The Pile)

Max Activating Token Index: 98

Text #14

Max Range: 1.9904. Min Range: -1.9904

Max Act: 0.6766. Min Act: -0.0000

Data Index: 218644 (The Pile)

Max Activating Token Index: 286

Text #15

Max Range: 1.9904. Min Range: -1.9904

Max Act: 1.0217. Min Act: 0.0000

Data Index: 1140963 (The Pile)

Max Activating Token Index: 748

Text #16

Max Range: 1.9904. Min Range: -1.9904

Max Act: 0.8666. Min Act: 0.0000

Data Index: 254074 (The Pile)

Max Activating Token Index: 388

Text #17

Max Range: 1.9904. Min Range: -1.9904

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1629526 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 1.9904. Min Range: -1.9904

Max Act: 0.9149. Min Act: -0.0000

Data Index: 677721 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 1.9904. Min Range: -1.9904

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1625556 (The Pile)

Max Activating Token Index: 153