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

Dataset: The Pile

Neuron 3132 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.8923. Min Act: -0.0000

Data Index: 344439 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1089438 (The Pile)

Max Activating Token Index: 158

Text #2

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.6325. Min Act: -0.0000

Data Index: 158386 (The Pile)

Max Activating Token Index: 152

Text #3

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1832233 (The Pile)

Max Activating Token Index: 602

Text #4

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5509. Min Act: -0.0000

Data Index: 737308 (The Pile)

Max Activating Token Index: 85

Text #5

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1838354 (The Pile)

Max Activating Token Index: 470

Text #6

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1642049 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1842223 (The Pile)

Max Activating Token Index: 309

Text #8

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5362. Min Act: -0.0000

Data Index: 691440 (The Pile)

Max Activating Token Index: 806

Text #9

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.4906. Min Act: -0.0000

Data Index: 1563758 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5007. Min Act: -0.0000

Data Index: 400556 (The Pile)

Max Activating Token Index: 241

Text #11

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1482859 (The Pile)

Max Activating Token Index: 660

Text #12

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5082. Min Act: -0.0000

Data Index: 33856 (The Pile)

Max Activating Token Index: 960

Text #13

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1832307 (The Pile)

Max Activating Token Index: 138

Text #14

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1173310 (The Pile)

Max Activating Token Index: 567

Text #15

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.4797. Min Act: -0.0000

Data Index: 838059 (The Pile)

Max Activating Token Index: 916

Text #16

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.4492. Min Act: -0.0000

Data Index: 127191 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1536004 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1296044 (The Pile)

Max Activating Token Index: 280

Text #19

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1087196 (The Pile)

Max Activating Token Index: 489