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

Dataset: The Pile

Neuron 2549 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: 0.6781. Min Range: -0.6781

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1204110 (The Pile)

Max Activating Token Index: 103

Text #1

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1054554 (The Pile)

Max Activating Token Index: 412

Text #2

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1561608 (The Pile)

Max Activating Token Index: 67

Text #3

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6468. Min Act: -0.0000

Data Index: 125760 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6781. Min Act: -0.0000

Data Index: 326502 (The Pile)

Max Activating Token Index: 815

Text #5

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5484. Min Act: -0.0000

Data Index: 121250 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5356. Min Act: -0.0000

Data Index: 828132 (The Pile)

Max Activating Token Index: 335

Text #7

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5493. Min Act: -0.0000

Data Index: 520174 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5227. Min Act: -0.0000

Data Index: 364070 (The Pile)

Max Activating Token Index: 197

Text #9

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5318. Min Act: -0.0000

Data Index: 635002 (The Pile)

Max Activating Token Index: 329

Text #10

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6099. Min Act: -0.0000

Data Index: 247474 (The Pile)

Max Activating Token Index: 881

Text #11

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4905. Min Act: -0.0000

Data Index: 973819 (The Pile)

Max Activating Token Index: 602

Text #12

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4646. Min Act: -0.0000

Data Index: 457299 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1409723 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1231523 (The Pile)

Max Activating Token Index: 842

Text #15

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5006. Min Act: -0.0000

Data Index: 853126 (The Pile)

Max Activating Token Index: 254

Text #16

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4996. Min Act: -0.0000

Data Index: 957883 (The Pile)

Max Activating Token Index: 672

Text #17

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5119. Min Act: -0.0000

Data Index: 789024 (The Pile)

Max Activating Token Index: 865

Text #18

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.5160. Min Act: -0.0001

Data Index: 292589 (The Pile)

Max Activating Token Index: 665

Text #19

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1679710 (The Pile)

Max Activating Token Index: 807