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

Dataset: The Pile

Neuron 1942 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8858. Min Act: -0.0000

Data Index: 785212 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1210171 (The Pile)

Max Activating Token Index: 489

Text #2

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1631146 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1483600 (The Pile)

Max Activating Token Index: 664

Text #4

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.7541. Min Act: -0.0000

Data Index: 1782799 (The Pile)

Max Activating Token Index: 528

Text #5

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.7756. Min Act: -0.0000

Data Index: 463014 (The Pile)

Max Activating Token Index: 182

Text #6

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.7513. Min Act: -0.0000

Data Index: 64553 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.7214. Min Act: -0.0000

Data Index: 466057 (The Pile)

Max Activating Token Index: 922

Text #8

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1413964 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.7444. Min Act: -0.0000

Data Index: 1809959 (The Pile)

Max Activating Token Index: 9

Text #10

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6077. Min Act: -0.0000

Data Index: 231447 (The Pile)

Max Activating Token Index: 487

Text #11

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6787. Min Act: -0.0000

Data Index: 330970 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6351. Min Act: -0.0000

Data Index: 152234 (The Pile)

Max Activating Token Index: 1018

Text #13

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6827. Min Act: -0.0000

Data Index: 114400 (The Pile)

Max Activating Token Index: 59

Text #14

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6147. Min Act: -0.0000

Data Index: 349353 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1653307 (The Pile)

Max Activating Token Index: 500

Text #16

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6870. Min Act: -0.0000

Data Index: 960303 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1736448 (The Pile)

Max Activating Token Index: 297

Text #18

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6328. Min Act: -0.0000

Data Index: 505667 (The Pile)

Max Activating Token Index: 215

Text #19

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6691. Min Act: -0.0000

Data Index: 620885 (The Pile)

Max Activating Token Index: 679