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

Dataset: The Pile

Neuron 2425 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: 0.4502. Min Range: -0.4502

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1577930 (The Pile)

Max Activating Token Index: 783

Text #1

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4044. Min Act: -0.0000

Data Index: 1062291 (The Pile)

Max Activating Token Index: 722

Text #2

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4158. Min Act: -0.0000

Data Index: 872885 (The Pile)

Max Activating Token Index: 985

Text #3

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3387. Min Act: -0.0000

Data Index: 1863167 (The Pile)

Max Activating Token Index: 603

Text #4

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3813. Min Act: -0.0000

Data Index: 110882 (The Pile)

Max Activating Token Index: 395

Text #5

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1660685 (The Pile)

Max Activating Token Index: 559

Text #6

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3739. Min Act: -0.0000

Data Index: 687140 (The Pile)

Max Activating Token Index: 521

Text #7

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3295. Min Act: -0.0000

Data Index: 834140 (The Pile)

Max Activating Token Index: 932

Text #8

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1849051 (The Pile)

Max Activating Token Index: 936

Text #9

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1960828 (The Pile)

Max Activating Token Index: 971

Text #10

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1066372 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3162. Min Act: -0.0000

Data Index: 880920 (The Pile)

Max Activating Token Index: 542

Text #12

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1617500 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3491. Min Act: -0.0000

Data Index: 54889 (The Pile)

Max Activating Token Index: 690

Text #14

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1557665 (The Pile)

Max Activating Token Index: 247

Text #15

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1434784 (The Pile)

Max Activating Token Index: 589

Text #16

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3249. Min Act: -0.0000

Data Index: 821325 (The Pile)

Max Activating Token Index: 672

Text #17

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3120. Min Act: -0.0000

Data Index: 319519 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3010. Min Act: -0.0000

Data Index: 296023 (The Pile)

Max Activating Token Index: 511

Text #19

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1829305 (The Pile)

Max Activating Token Index: 838