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

Dataset: The Pile

Neuron 926 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: 0.5658. Min Range: -0.5658

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1084993 (The Pile)

Max Activating Token Index: 599

Text #1

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1627121 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.5294. Min Act: 0.0000

Data Index: 1553909 (The Pile)

Max Activating Token Index: 766

Text #3

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.5329. Min Act: 0.0000

Data Index: 1470172 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1062212 (The Pile)

Max Activating Token Index: 579

Text #5

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1409323 (The Pile)

Max Activating Token Index: 555

Text #6

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4293. Min Act: -0.0000

Data Index: 150817 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4161. Min Act: -0.0000

Data Index: 1270509 (The Pile)

Max Activating Token Index: 880

Text #8

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4131. Min Act: -0.0000

Data Index: 488414 (The Pile)

Max Activating Token Index: 591

Text #9

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3910. Min Act: -0.0000

Data Index: 469301 (The Pile)

Max Activating Token Index: 27

Text #10

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1694646 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3885. Min Act: -0.0000

Data Index: 1330341 (The Pile)

Max Activating Token Index: 968

Text #12

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1368273 (The Pile)

Max Activating Token Index: 986

Text #13

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1385217 (The Pile)

Max Activating Token Index: 425

Text #14

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1494409 (The Pile)

Max Activating Token Index: 456

Text #15

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3541. Min Act: -0.0000

Data Index: 307225 (The Pile)

Max Activating Token Index: 391

Text #16

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1437789 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3343. Min Act: -0.0000

Data Index: 635829 (The Pile)

Max Activating Token Index: 745

Text #18

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3562. Min Act: -0.0000

Data Index: 393825 (The Pile)

Max Activating Token Index: 686

Text #19

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3375. Min Act: -0.0000

Data Index: 228706 (The Pile)

Max Activating Token Index: 784