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

Dataset: The Pile

Neuron 376 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3530. Min Range: -5.3530

Max Act: 5.3530. Min Act: -0.0000

Data Index: 859849 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 5.3530. Min Range: -5.3530

Max Act: 4.7048. Min Act: -0.0000

Data Index: 1511752 (The Pile)

Max Activating Token Index: 476

Text #2

Max Range: 5.3530. Min Range: -5.3530

Max Act: 4.4714. Min Act: -0.0000

Data Index: 186138 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 5.3530. Min Range: -5.3530

Max Act: 4.5901. Min Act: -0.0000

Data Index: 1333530 (The Pile)

Max Activating Token Index: 43

Text #4

Max Range: 5.3530. Min Range: -5.3530

Max Act: 4.2344. Min Act: -0.0000

Data Index: 721381 (The Pile)

Max Activating Token Index: 569

Text #5

Max Range: 5.3530. Min Range: -5.3530

Max Act: 4.2631. Min Act: -0.0000

Data Index: 118000 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 5.3530. Min Range: -5.3530

Max Act: 4.1975. Min Act: -0.0000

Data Index: 1427199 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 5.3530. Min Range: -5.3530

Max Act: 4.3760. Min Act: -0.0000

Data Index: 721615 (The Pile)

Max Activating Token Index: 685

Text #8

Max Range: 5.3530. Min Range: -5.3530

Max Act: 4.1457. Min Act: -0.0000

Data Index: 812882 (The Pile)

Max Activating Token Index: 21

Text #9

Max Range: 5.3530. Min Range: -5.3530

Max Act: 4.3247. Min Act: -0.0000

Data Index: 465726 (The Pile)

Max Activating Token Index: 678

Text #10

Max Range: 5.3530. Min Range: -5.3530

Max Act: 4.1675. Min Act: -0.0000

Data Index: 1624609 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 5.3530. Min Range: -5.3530

Max Act: 4.1042. Min Act: -0.0000

Data Index: 610051 (The Pile)

Max Activating Token Index: 167

Text #12

Max Range: 5.3530. Min Range: -5.3530

Max Act: 3.9049. Min Act: -0.0000

Data Index: 331915 (The Pile)

Max Activating Token Index: 855

Text #13

Max Range: 5.3530. Min Range: -5.3530

Max Act: 4.0358. Min Act: -0.0000

Data Index: 1538031 (The Pile)

Max Activating Token Index: 481

Text #14

Max Range: 5.3530. Min Range: -5.3530

Max Act: 4.0338. Min Act: -0.0000

Data Index: 1621351 (The Pile)

Max Activating Token Index: 262

Text #15

Max Range: 5.3530. Min Range: -5.3530

Max Act: 4.1375. Min Act: -0.0000

Data Index: 1594772 (The Pile)

Max Activating Token Index: 495

Text #16

Max Range: 5.3530. Min Range: -5.3530

Max Act: 3.8574. Min Act: -0.0000

Data Index: 1426278 (The Pile)

Max Activating Token Index: 451

Text #17

Max Range: 5.3530. Min Range: -5.3530

Max Act: 3.6459. Min Act: -0.0000

Data Index: 1531388 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 5.3530. Min Range: -5.3530

Max Act: 3.8566. Min Act: -0.0000

Data Index: 1448166 (The Pile)

Max Activating Token Index: 679

Text #19

Max Range: 5.3530. Min Range: -5.3530

Max Act: 3.7921. Min Act: -0.0000

Data Index: 737619 (The Pile)

Max Activating Token Index: 278