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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2629 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1589386 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1515596 (Python Code)

Max Activating Token Index: 491

Text #2

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1380053 (Python Code)

Max Activating Token Index: 680

Text #3

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1656897 (Python Code)

Max Activating Token Index: 396

Text #4

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1489009 (Python Code)

Max Activating Token Index: 930

Text #5

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1364697 (Python Code)

Max Activating Token Index: 664

Text #6

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1654130 (Python Code)

Max Activating Token Index: 197

Text #7

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1480504 (Python Code)

Max Activating Token Index: 842

Text #8

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1476549 (Python Code)

Max Activating Token Index: 628

Text #9

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1441710 (Python Code)

Max Activating Token Index: 499

Text #10

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3901. Min Act: -0.0000

Data Index: 245450 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1374156 (Python Code)

Max Activating Token Index: 870

Text #12

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1587462 (Python Code)

Max Activating Token Index: 262

Text #13

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1483727 (Python Code)

Max Activating Token Index: 234

Text #14

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1464540 (Python Code)

Max Activating Token Index: 640

Text #15

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1609758 (Python Code)

Max Activating Token Index: 686

Text #16

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3661. Min Act: -0.0000

Data Index: 1466180 (Python Code)

Max Activating Token Index: 901

Text #17

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1622027 (Python Code)

Max Activating Token Index: 118

Text #18

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1442938 (Python Code)

Max Activating Token Index: 427

Text #19

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1622649 (Python Code)

Max Activating Token Index: 792