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

Dataset: The Pile

Neuron 3944 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: 0.7530. Min Range: -0.7530

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1446215 (The Pile)

Max Activating Token Index: 971

Text #1

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.5455. Min Act: -0.0000

Data Index: 1953224 (The Pile)

Max Activating Token Index: 183

Text #2

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.5778. Min Act: -0.0000

Data Index: 209359 (The Pile)

Max Activating Token Index: 316

Text #3

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.4605. Min Act: -0.0000

Data Index: 562186 (The Pile)

Max Activating Token Index: 856

Text #4

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1125314 (The Pile)

Max Activating Token Index: 586

Text #5

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1968932 (The Pile)

Max Activating Token Index: 549

Text #6

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3867. Min Act: -0.0000

Data Index: 145129 (The Pile)

Max Activating Token Index: 445

Text #7

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3992. Min Act: -0.0000

Data Index: 408197 (The Pile)

Max Activating Token Index: 882

Text #8

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3980. Min Act: -0.0000

Data Index: 336104 (The Pile)

Max Activating Token Index: 266

Text #9

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3493. Min Act: -0.0000

Data Index: 373918 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3744. Min Act: -0.0000

Data Index: 48726 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1268564 (The Pile)

Max Activating Token Index: 381

Text #12

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3840. Min Act: -0.0000

Data Index: 911195 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3644. Min Act: -0.0000

Data Index: 976500 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1487339 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3365. Min Act: -0.0000

Data Index: 252674 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1317621 (The Pile)

Max Activating Token Index: 614

Text #17

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3117. Min Act: -0.0000

Data Index: 1537346 (The Pile)

Max Activating Token Index: 980

Text #18

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3354. Min Act: -0.0000

Data Index: 1244212 (The Pile)

Max Activating Token Index: 541

Text #19

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1436122 (The Pile)

Max Activating Token Index: 1015