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

Dataset: The Pile

Neuron 3533 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: 0.5040. Min Range: -0.5040

Max Act: 0.4715. Min Act: -0.0000

Data Index: 349196 (The Pile)

Max Activating Token Index: 132

Text #1

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1549434 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1331732 (The Pile)

Max Activating Token Index: 1008

Text #3

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1444905 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1207173 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1866635 (The Pile)

Max Activating Token Index: 503

Text #6

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1923419 (The Pile)

Max Activating Token Index: 763

Text #7

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1249365 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4321. Min Act: -0.0000

Data Index: 889172 (The Pile)

Max Activating Token Index: 22

Text #9

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4437. Min Act: -0.0000

Data Index: 31504 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1958926 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4282. Min Act: -0.0000

Data Index: 271281 (The Pile)

Max Activating Token Index: 321

Text #12

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4335. Min Act: -0.0000

Data Index: 575782 (The Pile)

Max Activating Token Index: 28

Text #13

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4421. Min Act: -0.0000

Data Index: 1396560 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3719. Min Act: -0.0000

Data Index: 953777 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1567002 (The Pile)

Max Activating Token Index: 70

Text #16

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3815. Min Act: -0.0000

Data Index: 449780 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3911. Min Act: -0.0000

Data Index: 734819 (The Pile)

Max Activating Token Index: 42

Text #18

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1833789 (The Pile)

Max Activating Token Index: 719

Text #19

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4082. Min Act: -0.0000

Data Index: 11149 (The Pile)

Max Activating Token Index: 146