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

Dataset: The Pile

Neuron 2472 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0996. Min Range: -1.0996

Max Act: 1.0996. Min Act: -0.0001

Data Index: 698024 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 1.0996. Min Range: -1.0996

Max Act: 1.0677. Min Act: -0.0000

Data Index: 1614567 (The Pile)

Max Activating Token Index: 64

Text #2

Max Range: 1.0996. Min Range: -1.0996

Max Act: 1.0260. Min Act: -0.0001

Data Index: 284768 (The Pile)

Max Activating Token Index: 399

Text #3

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.9847. Min Act: -0.0001

Data Index: 1274626 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 1.0996. Min Range: -1.0996

Max Act: 1.0463. Min Act: -0.0001

Data Index: 885762 (The Pile)

Max Activating Token Index: 930

Text #5

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.9591. Min Act: -0.0001

Data Index: 762426 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.9106. Min Act: -0.0001

Data Index: 1793267 (The Pile)

Max Activating Token Index: 158

Text #7

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.8959. Min Act: -0.0001

Data Index: 822155 (The Pile)

Max Activating Token Index: 312

Text #8

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.9162. Min Act: -0.0001

Data Index: 375397 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.9184. Min Act: -0.0001

Data Index: 65016 (The Pile)

Max Activating Token Index: 278

Text #10

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.9528. Min Act: -0.0001

Data Index: 1897571 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.9145. Min Act: -0.0001

Data Index: 658762 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.8962. Min Act: -0.0001

Data Index: 1535843 (The Pile)

Max Activating Token Index: 750

Text #13

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.9004. Min Act: -0.0001

Data Index: 1127492 (The Pile)

Max Activating Token Index: 533

Text #14

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.9288. Min Act: -0.0001

Data Index: 1496569 (The Pile)

Max Activating Token Index: 86

Text #15

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.9229. Min Act: -0.0001

Data Index: 1091841 (The Pile)

Max Activating Token Index: 253

Text #16

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.8676. Min Act: -0.0001

Data Index: 476714 (The Pile)

Max Activating Token Index: 118

Text #17

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.8706. Min Act: -0.0001

Data Index: 1130876 (The Pile)

Max Activating Token Index: 78

Text #18

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.8830. Min Act: -0.0001

Data Index: 1754081 (The Pile)

Max Activating Token Index: 925

Text #19

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.8856. Min Act: -0.0001

Data Index: 1748650 (The Pile)

Max Activating Token Index: 407