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

Dataset: The Pile

Neuron 3924 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: 0.3197. Min Range: -0.3197

Max Act: 0.3197. Min Act: -0.0000

Data Index: 579609 (The Pile)

Max Activating Token Index: 413

Text #1

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.3131. Min Act: -0.0000

Data Index: 837250 (The Pile)

Max Activating Token Index: 450

Text #2

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1644628 (The Pile)

Max Activating Token Index: 97

Text #3

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.3115. Min Act: -0.0000

Data Index: 887222 (The Pile)

Max Activating Token Index: 89

Text #4

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1535546 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2969. Min Act: -0.0000

Data Index: 951936 (The Pile)

Max Activating Token Index: 635

Text #6

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2604. Min Act: -0.0000

Data Index: 346466 (The Pile)

Max Activating Token Index: 925

Text #7

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2663. Min Act: -0.0000

Data Index: 754211 (The Pile)

Max Activating Token Index: 722

Text #8

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2823. Min Act: -0.0000

Data Index: 904187 (The Pile)

Max Activating Token Index: 663

Text #9

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2771. Min Act: -0.0000

Data Index: 1548642 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1275873 (The Pile)

Max Activating Token Index: 207

Text #11

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1817534 (The Pile)

Max Activating Token Index: 562

Text #12

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2649. Min Act: -0.0000

Data Index: 104509 (The Pile)

Max Activating Token Index: 202

Text #13

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2556. Min Act: -0.0000

Data Index: 967001 (The Pile)

Max Activating Token Index: 733

Text #14

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1630055 (The Pile)

Max Activating Token Index: 714

Text #15

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1729821 (The Pile)

Max Activating Token Index: 858

Text #16

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1136989 (The Pile)

Max Activating Token Index: 192

Text #17

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1964681 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1428365 (The Pile)

Max Activating Token Index: 360

Text #19

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2629. Min Act: -0.0000

Data Index: 1578005 (The Pile)

Max Activating Token Index: 361