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

Dataset: The Pile

Neuron 1503 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: 0.5629. Min Range: -0.5629

Max Act: 0.5193. Min Act: -0.0000

Data Index: 1220192 (The Pile)

Max Activating Token Index: 318

Text #1

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.5269. Min Act: -0.0000

Data Index: 467755 (The Pile)

Max Activating Token Index: 687

Text #2

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.5629. Min Act: -0.0000

Data Index: 1787931 (The Pile)

Max Activating Token Index: 568

Text #3

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.4861. Min Act: -0.0000

Data Index: 373869 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.4834. Min Act: -0.0000

Data Index: 1149220 (The Pile)

Max Activating Token Index: 293

Text #5

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.4925. Min Act: -0.0000

Data Index: 3675 (The Pile)

Max Activating Token Index: 763

Text #6

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.4821. Min Act: -0.0000

Data Index: 746943 (The Pile)

Max Activating Token Index: 560

Text #7

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1610817 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.4062. Min Act: -0.0000

Data Index: 311779 (The Pile)

Max Activating Token Index: 743

Text #9

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.4003. Min Act: -0.0000

Data Index: 611946 (The Pile)

Max Activating Token Index: 236

Text #10

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1520167 (The Pile)

Max Activating Token Index: 301

Text #11

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1713198 (The Pile)

Max Activating Token Index: 578

Text #12

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3883. Min Act: -0.0000

Data Index: 108278 (The Pile)

Max Activating Token Index: 651

Text #13

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3863. Min Act: -0.0000

Data Index: 511879 (The Pile)

Max Activating Token Index: 93

Text #14

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.4093. Min Act: -0.0000

Data Index: 195313 (The Pile)

Max Activating Token Index: 545

Text #15

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1727873 (The Pile)

Max Activating Token Index: 94

Text #16

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3919. Min Act: -0.0000

Data Index: 485682 (The Pile)

Max Activating Token Index: 688

Text #17

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1265289 (The Pile)

Max Activating Token Index: 959

Text #18

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.4293. Min Act: -0.0000

Data Index: 301849 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.3976. Min Act: -0.0000

Data Index: 936573 (The Pile)

Max Activating Token Index: 578