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

Dataset: The Pile

Neuron 1857 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: 1.2622. Min Range: -1.2622

Max Act: 1.2622. Min Act: -0.0000

Data Index: 774862 (The Pile)

Max Activating Token Index: 510

Text #1

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.2252. Min Act: -0.0000

Data Index: 1130918 (The Pile)

Max Activating Token Index: 410

Text #2

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1305843 (The Pile)

Max Activating Token Index: 134

Text #3

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1551. Min Act: -0.0000

Data Index: 219138 (The Pile)

Max Activating Token Index: 463

Text #4

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1239. Min Act: -0.0000

Data Index: 382794 (The Pile)

Max Activating Token Index: 993

Text #5

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1551. Min Act: -0.0000

Data Index: 480315 (The Pile)

Max Activating Token Index: 137

Text #6

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0758. Min Act: -0.0000

Data Index: 1457893 (The Pile)

Max Activating Token Index: 528

Text #7

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1023. Min Act: -0.0000

Data Index: 303991 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0958. Min Act: -0.0000

Data Index: 1142241 (The Pile)

Max Activating Token Index: 434

Text #9

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0913. Min Act: -0.0000

Data Index: 228442 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1184. Min Act: -0.0000

Data Index: 685981 (The Pile)

Max Activating Token Index: 684

Text #11

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0950. Min Act: -0.0000

Data Index: 96965 (The Pile)

Max Activating Token Index: 723

Text #12

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0636. Min Act: -0.0000

Data Index: 116550 (The Pile)

Max Activating Token Index: 803

Text #13

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0075. Min Act: -0.0000

Data Index: 53234 (The Pile)

Max Activating Token Index: 472

Text #14

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1184334 (The Pile)

Max Activating Token Index: 47

Text #15

Max Range: 1.2622. Min Range: -1.2622

Max Act: 0.9831. Min Act: -0.0000

Data Index: 456785 (The Pile)

Max Activating Token Index: 135

Text #16

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0492. Min Act: -0.0000

Data Index: 153643 (The Pile)

Max Activating Token Index: 48

Text #17

Max Range: 1.2622. Min Range: -1.2622

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1443901 (The Pile)

Max Activating Token Index: 1013

Text #18

Max Range: 1.2622. Min Range: -1.2622

Max Act: 0.9731. Min Act: -0.0000

Data Index: 503390 (The Pile)

Max Activating Token Index: 197

Text #19

Max Range: 1.2622. Min Range: -1.2622

Max Act: 0.9585. Min Act: -0.0000

Data Index: 448258 (The Pile)

Max Activating Token Index: 538