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

Dataset: The Pile

Neuron 3255 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: 1.7552. Min Range: -1.7552

Max Act: 1.7552. Min Act: -0.0000

Data Index: 1779377 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.2525. Min Act: -0.0000

Data Index: 770565 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.4933. Min Act: -0.0000

Data Index: 1526733 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.4631. Min Act: -0.0000

Data Index: 160898 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1263088 (The Pile)

Max Activating Token Index: 927

Text #5

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.3752. Min Act: -0.0000

Data Index: 1166617 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.0260. Min Act: -0.0000

Data Index: 308343 (The Pile)

Max Activating Token Index: 42

Text #7

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.0122. Min Act: -0.0000

Data Index: 1321593 (The Pile)

Max Activating Token Index: 806

Text #8

Max Range: 1.7552. Min Range: -1.7552

Max Act: 0.9876. Min Act: -0.0000

Data Index: 282218 (The Pile)

Max Activating Token Index: 915

Text #9

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.0396. Min Act: -0.0000

Data Index: 500356 (The Pile)

Max Activating Token Index: 1012

Text #10

Max Range: 1.7552. Min Range: -1.7552

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1836975 (The Pile)

Max Activating Token Index: 382

Text #11

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.0307. Min Act: -0.0000

Data Index: 621873 (The Pile)

Max Activating Token Index: 224

Text #12

Max Range: 1.7552. Min Range: -1.7552

Max Act: 0.9022. Min Act: -0.0000

Data Index: 714772 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 1.7552. Min Range: -1.7552

Max Act: 0.9305. Min Act: -0.0000

Data Index: 1642733 (The Pile)

Max Activating Token Index: 628

Text #14

Max Range: 1.7552. Min Range: -1.7552

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1190746 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 1.7552. Min Range: -1.7552

Max Act: 0.8497. Min Act: -0.0000

Data Index: 585486 (The Pile)

Max Activating Token Index: 137

Text #16

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1451655 (The Pile)

Max Activating Token Index: 922

Text #17

Max Range: 1.7552. Min Range: -1.7552

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1980265 (The Pile)

Max Activating Token Index: 836

Text #18

Max Range: 1.7552. Min Range: -1.7552

Max Act: 0.7862. Min Act: 0.0000

Data Index: 156092 (The Pile)

Max Activating Token Index: 586

Text #19

Max Range: 1.7552. Min Range: -1.7552

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1121833 (The Pile)

Max Activating Token Index: 481