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

Dataset: The Pile

Neuron 3471 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: 1.8882. Min Range: -1.8882

Max Act: 1.8882. Min Act: -0.0000

Data Index: 1544268 (The Pile)

Max Activating Token Index: 222

Text #1

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.4985. Min Act: -0.0000

Data Index: 1951621 (The Pile)

Max Activating Token Index: 489

Text #2

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.7121. Min Act: -0.0000

Data Index: 450026 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.5761. Min Act: -0.0000

Data Index: 1524527 (The Pile)

Max Activating Token Index: 150

Text #4

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.5917. Min Act: -0.0000

Data Index: 1786222 (The Pile)

Max Activating Token Index: 257

Text #5

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.5585. Min Act: -0.0000

Data Index: 1787292 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.5902. Min Act: -0.0000

Data Index: 334900 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.8122. Min Act: -0.0000

Data Index: 1980819 (The Pile)

Max Activating Token Index: 784

Text #8

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.4565. Min Act: -0.0000

Data Index: 1668070 (The Pile)

Max Activating Token Index: 329

Text #9

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.4510. Min Act: -0.0000

Data Index: 1434460 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.4606. Min Act: -0.0000

Data Index: 946159 (The Pile)

Max Activating Token Index: 894

Text #11

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3553. Min Act: -0.0000

Data Index: 777447 (The Pile)

Max Activating Token Index: 600

Text #12

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3452. Min Act: -0.0000

Data Index: 61032 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3338. Min Act: -0.0000

Data Index: 99451 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3384. Min Act: -0.0000

Data Index: 753827 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3073. Min Act: -0.0000

Data Index: 288993 (The Pile)

Max Activating Token Index: 725

Text #16

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.4661. Min Act: -0.0000

Data Index: 524204 (The Pile)

Max Activating Token Index: 797

Text #17

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3775. Min Act: -0.0000

Data Index: 184928 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.4256. Min Act: -0.0000

Data Index: 1038637 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3551. Min Act: -0.0000

Data Index: 1075061 (The Pile)

Max Activating Token Index: 574