Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4033 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.5611. Min Range: -3.5611

Max Act: 3.5611. Min Act: -0.0000

Data Index: 1502037 (The Pile)

Max Activating Token Index: 595

Text #1

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.9544. Min Act: -0.0000

Data Index: 449715 (The Pile)

Max Activating Token Index: 116

Text #2

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.9619. Min Act: -0.0000

Data Index: 638778 (The Pile)

Max Activating Token Index: 55

Text #3

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.9537. Min Act: -0.0000

Data Index: 1632714 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.9646. Min Act: -0.0000

Data Index: 1753657 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.4819. Min Act: -0.0000

Data Index: 1900891 (The Pile)

Max Activating Token Index: 719

Text #6

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.5121. Min Act: -0.0000

Data Index: 1273033 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.5942. Min Act: -0.0000

Data Index: 19992 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.6009. Min Act: -0.0000

Data Index: 811058 (The Pile)

Max Activating Token Index: 90

Text #9

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.4314. Min Act: -0.0000

Data Index: 1958598 (The Pile)

Max Activating Token Index: 865

Text #10

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.4473. Min Act: -0.0000

Data Index: 1214308 (The Pile)

Max Activating Token Index: 526

Text #11

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.8356. Min Act: -0.0000

Data Index: 1159396 (The Pile)

Max Activating Token Index: 121

Text #12

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.6429. Min Act: -0.0000

Data Index: 310631 (The Pile)

Max Activating Token Index: 114

Text #13

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.3907. Min Act: -0.0000

Data Index: 196650 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.4941. Min Act: -0.0000

Data Index: 1860412 (The Pile)

Max Activating Token Index: 318

Text #15

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.4842. Min Act: -0.0000

Data Index: 494561 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.4730. Min Act: -0.0000

Data Index: 1325213 (The Pile)

Max Activating Token Index: 115

Text #17

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.3223. Min Act: -0.0000

Data Index: 1441917 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.4304. Min Act: -0.0000

Data Index: 860757 (The Pile)

Max Activating Token Index: 24

Text #19

Max Range: 3.5611. Min Range: -3.5611

Max Act: 2.4203. Min Act: -0.0000

Data Index: 591424 (The Pile)

Max Activating Token Index: 78