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

Dataset: The Pile

Neuron 848 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: 0.9764. Min Range: -0.9764

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1978692 (The Pile)

Max Activating Token Index: 191

Text #1

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.9764. Min Act: -0.0000

Data Index: 782708 (The Pile)

Max Activating Token Index: 127

Text #2

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1914256 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.9530. Min Act: -0.0000

Data Index: 799664 (The Pile)

Max Activating Token Index: 47

Text #4

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1458149 (The Pile)

Max Activating Token Index: 565

Text #5

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8460. Min Act: -0.0000

Data Index: 499114 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1843730 (The Pile)

Max Activating Token Index: 740

Text #7

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8017. Min Act: -0.0000

Data Index: 1933050 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1259785 (The Pile)

Max Activating Token Index: 345

Text #9

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.7096. Min Act: -0.0000

Data Index: 764060 (The Pile)

Max Activating Token Index: 639

Text #10

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1573293 (The Pile)

Max Activating Token Index: 619

Text #11

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1738319 (The Pile)

Max Activating Token Index: 284

Text #12

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.7237. Min Act: -0.0000

Data Index: 742459 (The Pile)

Max Activating Token Index: 343

Text #13

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1908440 (The Pile)

Max Activating Token Index: 500

Text #14

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8005. Min Act: -0.0000

Data Index: 391011 (The Pile)

Max Activating Token Index: 778

Text #15

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1716206 (The Pile)

Max Activating Token Index: 855

Text #16

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.7159. Min Act: -0.0000

Data Index: 899513 (The Pile)

Max Activating Token Index: 449

Text #17

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6901. Min Act: -0.0000

Data Index: 589053 (The Pile)

Max Activating Token Index: 341

Text #18

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1318332 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1568087 (The Pile)

Max Activating Token Index: 429