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

Dataset: The Pile

Neuron 2719 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.9246. Min Act: -0.0000

Data Index: 1633038 (The Pile)

Max Activating Token Index: 420

Text #1

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8526. Min Act: -0.0000

Data Index: 149062 (The Pile)

Max Activating Token Index: 396

Text #2

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8454. Min Act: -0.0000

Data Index: 820435 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8507. Min Act: -0.0000

Data Index: 281155 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1351452 (The Pile)

Max Activating Token Index: 626

Text #5

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8858. Min Act: -0.0000

Data Index: 1615762 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1992609 (The Pile)

Max Activating Token Index: 134

Text #7

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1195777 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8121. Min Act: -0.0000

Data Index: 591247 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8056. Min Act: -0.0000

Data Index: 740086 (The Pile)

Max Activating Token Index: 349

Text #10

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1144850 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8003. Min Act: -0.0000

Data Index: 67226 (The Pile)

Max Activating Token Index: 864

Text #12

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1025085 (The Pile)

Max Activating Token Index: 820

Text #13

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8042. Min Act: -0.0000

Data Index: 54251 (The Pile)

Max Activating Token Index: 364

Text #14

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1706658 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7816. Min Act: -0.0000

Data Index: 845080 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1026607 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7965. Min Act: -0.0000

Data Index: 574718 (The Pile)

Max Activating Token Index: 449

Text #18

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7693. Min Act: -0.0000

Data Index: 1823408 (The Pile)

Max Activating Token Index: 363

Text #19

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7390. Min Act: -0.0000

Data Index: 932506 (The Pile)

Max Activating Token Index: 337