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

Dataset: The Pile

Neuron 3275 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1385042 (The Pile)

Max Activating Token Index: 38

Text #1

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7197. Min Act: -0.0000

Data Index: 941557 (The Pile)

Max Activating Token Index: 641

Text #2

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1329639 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1578725 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6645. Min Act: -0.0000

Data Index: 731352 (The Pile)

Max Activating Token Index: 418

Text #5

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1748377 (The Pile)

Max Activating Token Index: 246

Text #6

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6526. Min Act: -0.0000

Data Index: 778267 (The Pile)

Max Activating Token Index: 972

Text #7

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6397. Min Act: -0.0000

Data Index: 79616 (The Pile)

Max Activating Token Index: 730

Text #8

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.5908. Min Act: -0.0000

Data Index: 806156 (The Pile)

Max Activating Token Index: 603

Text #9

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.5736. Min Act: -0.0000

Data Index: 941744 (The Pile)

Max Activating Token Index: 742

Text #10

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1445724 (The Pile)

Max Activating Token Index: 81

Text #11

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1039975 (The Pile)

Max Activating Token Index: 548

Text #12

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1469788 (The Pile)

Max Activating Token Index: 786

Text #13

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.5555. Min Act: -0.0000

Data Index: 476468 (The Pile)

Max Activating Token Index: 351

Text #14

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1080032 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1396192 (The Pile)

Max Activating Token Index: 726

Text #16

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1382578 (The Pile)

Max Activating Token Index: 683

Text #17

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1600738 (The Pile)

Max Activating Token Index: 734

Text #18

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1783298 (The Pile)

Max Activating Token Index: 562

Text #19

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1551701 (The Pile)

Max Activating Token Index: 502