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

Dataset: The Pile

Neuron 3849 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4283. Min Act: -0.0000

Data Index: 1810211 (The Pile)

Max Activating Token Index: 622

Text #1

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.0286. Min Act: -0.0000

Data Index: 1407702 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.1512. Min Act: -0.0000

Data Index: 1996044 (The Pile)

Max Activating Token Index: 373

Text #3

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.7534. Min Act: -0.0000

Data Index: 1072039 (The Pile)

Max Activating Token Index: 897

Text #4

Max Range: 3.7534. Min Range: -3.7534

Max Act: 2.9825. Min Act: -0.0000

Data Index: 1620598 (The Pile)

Max Activating Token Index: 614

Text #5

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.2541. Min Act: -0.0000

Data Index: 1203271 (The Pile)

Max Activating Token Index: 237

Text #6

Max Range: 3.7534. Min Range: -3.7534

Max Act: 2.9460. Min Act: -0.0000

Data Index: 665960 (The Pile)

Max Activating Token Index: 470

Text #7

Max Range: 3.7534. Min Range: -3.7534

Max Act: 2.8756. Min Act: -0.0000

Data Index: 960950 (The Pile)

Max Activating Token Index: 160

Text #8

Max Range: 3.7534. Min Range: -3.7534

Max Act: 2.9807. Min Act: -0.0000

Data Index: 1658754 (The Pile)

Max Activating Token Index: 457

Text #9

Max Range: 3.7534. Min Range: -3.7534

Max Act: 2.9957. Min Act: -0.0000

Data Index: 356048 (The Pile)

Max Activating Token Index: 903

Text #10

Max Range: 3.7534. Min Range: -3.7534

Max Act: 2.9427. Min Act: -0.0000

Data Index: 1897098 (The Pile)

Max Activating Token Index: 428

Text #11

Max Range: 3.7534. Min Range: -3.7534

Max Act: 2.5919. Min Act: -0.0000

Data Index: 195675 (The Pile)

Max Activating Token Index: 846

Text #12

Max Range: 3.7534. Min Range: -3.7534

Max Act: 2.9099. Min Act: -0.0000

Data Index: 1331321 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 3.7534. Min Range: -3.7534

Max Act: 2.8656. Min Act: -0.0000

Data Index: 1871030 (The Pile)

Max Activating Token Index: 816

Text #14

Max Range: 3.7534. Min Range: -3.7534

Max Act: 2.9993. Min Act: -0.0000

Data Index: 1322239 (The Pile)

Max Activating Token Index: 303

Text #15

Max Range: 3.7534. Min Range: -3.7534

Max Act: 2.8433. Min Act: -0.0000

Data Index: 1492362 (The Pile)

Max Activating Token Index: 279

Text #16

Max Range: 3.7534. Min Range: -3.7534

Max Act: 2.7646. Min Act: -0.0000

Data Index: 892930 (The Pile)

Max Activating Token Index: 664

Text #17

Max Range: 3.7534. Min Range: -3.7534

Max Act: 2.5727. Min Act: -0.0000

Data Index: 1407291 (The Pile)

Max Activating Token Index: 993

Text #18

Max Range: 3.7534. Min Range: -3.7534

Max Act: 2.4177. Min Act: -0.0000

Data Index: 136463 (The Pile)

Max Activating Token Index: 120

Text #19

Max Range: 3.7534. Min Range: -3.7534

Max Act: 2.2388. Min Act: -0.0000

Data Index: 4216 (The Pile)

Max Activating Token Index: 669