Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 464 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0233. Min Range: -1.0233

Max Act: 1.0043. Min Act: -0.0000

Data Index: 2240 (The Pile)

Max Activating Token Index: 344

Text #1

Max Range: 1.0233. Min Range: -1.0233

Max Act: 1.0233. Min Act: -0.0000

Data Index: 115162 (The Pile)

Max Activating Token Index: 661

Text #2

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.9764. Min Act: -0.0000

Data Index: 655990 (The Pile)

Max Activating Token Index: 478

Text #3

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1777425 (The Pile)

Max Activating Token Index: 670

Text #4

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.8773. Min Act: -0.0000

Data Index: 475337 (The Pile)

Max Activating Token Index: 174

Text #5

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.9099. Min Act: -0.0000

Data Index: 1872167 (The Pile)

Max Activating Token Index: 527

Text #6

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1998394 (The Pile)

Max Activating Token Index: 404

Text #7

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1408522 (The Pile)

Max Activating Token Index: 277

Text #8

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.8870. Min Act: -0.0000

Data Index: 839657 (The Pile)

Max Activating Token Index: 253

Text #9

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.8662. Min Act: -0.0000

Data Index: 1603153 (The Pile)

Max Activating Token Index: 506

Text #10

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1507185 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.7980. Min Act: -0.0000

Data Index: 187033 (The Pile)

Max Activating Token Index: 665

Text #12

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.8415. Min Act: -0.0000

Data Index: 52615 (The Pile)

Max Activating Token Index: 589

Text #13

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1904320 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.9072. Min Act: -0.0000

Data Index: 763638 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.7933. Min Act: -0.0000

Data Index: 1137692 (The Pile)

Max Activating Token Index: 613

Text #16

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.8333. Min Act: -0.0000

Data Index: 138910 (The Pile)

Max Activating Token Index: 725

Text #17

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1196640 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.7745. Min Act: -0.0000

Data Index: 1165801 (The Pile)

Max Activating Token Index: 112

Text #19

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.7620. Min Act: -0.0000

Data Index: 180018 (The Pile)

Max Activating Token Index: 796