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

Dataset: The Pile

Neuron 1751 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.9689. Min Act: -0.0000

Data Index: 911195 (The Pile)

Max Activating Token Index: 846

Text #1

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.9009. Min Act: -0.0000

Data Index: 1318630 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1590416 (The Pile)

Max Activating Token Index: 861

Text #3

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.8830. Min Act: -0.0000

Data Index: 910371 (The Pile)

Max Activating Token Index: 823

Text #4

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1072858 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.8505. Min Act: -0.0000

Data Index: 1669451 (The Pile)

Max Activating Token Index: 386

Text #6

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.8230. Min Act: -0.0000

Data Index: 753276 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7828. Min Act: -0.0000

Data Index: 931310 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7790. Min Act: -0.0000

Data Index: 474214 (The Pile)

Max Activating Token Index: 117

Text #9

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7723. Min Act: -0.0000

Data Index: 976320 (The Pile)

Max Activating Token Index: 350

Text #10

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7822. Min Act: -0.0000

Data Index: 993645 (The Pile)

Max Activating Token Index: 335

Text #11

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7833. Min Act: -0.0000

Data Index: 239577 (The Pile)

Max Activating Token Index: 626

Text #12

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7989. Min Act: -0.0000

Data Index: 394122 (The Pile)

Max Activating Token Index: 196

Text #13

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7972. Min Act: -0.0000

Data Index: 600471 (The Pile)

Max Activating Token Index: 850

Text #14

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7433. Min Act: -0.0000

Data Index: 220060 (The Pile)

Max Activating Token Index: 669

Text #15

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7566. Min Act: -0.0000

Data Index: 297286 (The Pile)

Max Activating Token Index: 855

Text #16

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1601219 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7039. Min Act: -0.0000

Data Index: 783995 (The Pile)

Max Activating Token Index: 77

Text #18

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1676665 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7325. Min Act: -0.0000

Data Index: 1593943 (The Pile)

Max Activating Token Index: 549