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

Dataset: The Pile

Neuron 3568 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.9392. Min Act: -0.0000

Data Index: 503512 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.9244. Min Act: -0.0000

Data Index: 1028306 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1249147 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1124634 (The Pile)

Max Activating Token Index: 327

Text #4

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.8580. Min Act: -0.0000

Data Index: 688892 (The Pile)

Max Activating Token Index: 185

Text #5

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.7917. Min Act: -0.0000

Data Index: 497705 (The Pile)

Max Activating Token Index: 601

Text #6

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.8807. Min Act: -0.0000

Data Index: 311462 (The Pile)

Max Activating Token Index: 125

Text #7

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1000587 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.7541. Min Act: -0.0000

Data Index: 993599 (The Pile)

Max Activating Token Index: 622

Text #9

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.7337. Min Act: -0.0000

Data Index: 79924 (The Pile)

Max Activating Token Index: 366

Text #10

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1123991 (The Pile)

Max Activating Token Index: 349

Text #11

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.7644. Min Act: -0.0000

Data Index: 345366 (The Pile)

Max Activating Token Index: 195

Text #12

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.6849. Min Act: -0.0000

Data Index: 303525 (The Pile)

Max Activating Token Index: 129

Text #13

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.6974. Min Act: -0.0000

Data Index: 892196 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1346591 (The Pile)

Max Activating Token Index: 243

Text #15

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.6255. Min Act: -0.0000

Data Index: 875787 (The Pile)

Max Activating Token Index: 538

Text #16

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.6052. Min Act: -0.0000

Data Index: 413678 (The Pile)

Max Activating Token Index: 395

Text #17

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1156954 (The Pile)

Max Activating Token Index: 241

Text #18

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.5881. Min Act: 0.0000

Data Index: 1639086 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 0.9853. Min Range: -0.9853

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1026122 (The Pile)

Max Activating Token Index: 392