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

Dataset: The Pile

Neuron 2805 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: 1.9053. Min Range: -1.9053

Max Act: 1.9053. Min Act: -0.0000

Data Index: 1710861 (The Pile)

Max Activating Token Index: 732

Text #1

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.5801. Min Act: -0.0000

Data Index: 1652303 (The Pile)

Max Activating Token Index: 807

Text #2

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.5452. Min Act: -0.0000

Data Index: 461944 (The Pile)

Max Activating Token Index: 831

Text #3

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.5754. Min Act: -0.0000

Data Index: 1768829 (The Pile)

Max Activating Token Index: 412

Text #4

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.2424. Min Act: -0.0000

Data Index: 337389 (The Pile)

Max Activating Token Index: 712

Text #5

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.3631. Min Act: -0.0000

Data Index: 595325 (The Pile)

Max Activating Token Index: 471

Text #6

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.3650. Min Act: -0.0000

Data Index: 1864870 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.3779. Min Act: -0.0000

Data Index: 1318762 (The Pile)

Max Activating Token Index: 630

Text #8

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.2975. Min Act: -0.0000

Data Index: 920191 (The Pile)

Max Activating Token Index: 902

Text #9

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.2750. Min Act: -0.0000

Data Index: 1251653 (The Pile)

Max Activating Token Index: 868

Text #10

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.2895. Min Act: -0.0000

Data Index: 1579559 (The Pile)

Max Activating Token Index: 672

Text #11

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.2914. Min Act: -0.0000

Data Index: 1445267 (The Pile)

Max Activating Token Index: 865

Text #12

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.1716. Min Act: -0.0000

Data Index: 1557148 (The Pile)

Max Activating Token Index: 209

Text #13

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.1589. Min Act: -0.0000

Data Index: 619212 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.1597. Min Act: -0.0000

Data Index: 47519 (The Pile)

Max Activating Token Index: 709

Text #15

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.2195. Min Act: -0.0000

Data Index: 799601 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 1.9053. Min Range: -1.9053

Max Act: 0.9948. Min Act: -0.0000

Data Index: 1338143 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.1382. Min Act: -0.0000

Data Index: 1249190 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.0598. Min Act: -0.0000

Data Index: 1366970 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 1.9053. Min Range: -1.9053

Max Act: 1.1543. Min Act: -0.0000

Data Index: 1839813 (The Pile)

Max Activating Token Index: 747