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

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

Neuron 3716 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: 0.4955. Min Range: -0.4955

Max Act: 0.4756. Min Act: 0.0001

Data Index: 1022813 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4955. Min Act: -0.0000

Data Index: 321854 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1031033 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4550. Min Act: 0.0000

Data Index: 1008507 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4521. Min Act: -0.0000

Data Index: 574666 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4617. Min Act: -0.0000

Data Index: 971361 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3608. Min Act: -0.0000

Data Index: 549768 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4264. Min Act: -0.0000

Data Index: 400822 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4203. Min Act: -0.0000

Data Index: 907734 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3418. Min Act: -0.0000

Data Index: 730044 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3978. Min Act: 0.0000

Data Index: 1206985 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3993. Min Act: -0.0000

Data Index: 632924 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3991. Min Act: 0.0000

Data Index: 641270 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1040214 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1156532 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3783. Min Act: 0.0000

Data Index: 1314724 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4012. Min Act: 0.0000

Data Index: 632617 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1292182 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.4633. Min Act: -0.0000

Data Index: 44996 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.4955. Min Range: -0.4955

Max Act: 0.3844. Min Act: -0.0000

Data Index: 905970 (C4 (Web Text))

Max Activating Token Index: 760