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

Dataset: The Pile

Neuron 2946 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1110152 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4521. Min Act: -0.0000

Data Index: 141862 (The Pile)

Max Activating Token Index: 856

Text #2

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4243. Min Act: -0.0000

Data Index: 274002 (The Pile)

Max Activating Token Index: 422

Text #3

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1957700 (The Pile)

Max Activating Token Index: 722

Text #4

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1397963 (The Pile)

Max Activating Token Index: 924

Text #5

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3913. Min Act: -0.0000

Data Index: 696420 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3866. Min Act: -0.0000

Data Index: 135515 (The Pile)

Max Activating Token Index: 855

Text #7

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1393294 (The Pile)

Max Activating Token Index: 149

Text #8

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3817. Min Act: -0.0000

Data Index: 553915 (The Pile)

Max Activating Token Index: 248

Text #9

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1010249 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4068. Min Act: -0.0000

Data Index: 421725 (The Pile)

Max Activating Token Index: 861

Text #11

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3940. Min Act: -0.0000

Data Index: 141762 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3885. Min Act: -0.0000

Data Index: 1083644 (The Pile)

Max Activating Token Index: 654

Text #13

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3873. Min Act: -0.0000

Data Index: 383378 (The Pile)

Max Activating Token Index: 423

Text #14

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1417581 (The Pile)

Max Activating Token Index: 72

Text #15

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3559. Min Act: -0.0000

Data Index: 282131 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3604. Min Act: -0.0000

Data Index: 594525 (The Pile)

Max Activating Token Index: 851

Text #17

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3688. Min Act: -0.0000

Data Index: 323959 (The Pile)

Max Activating Token Index: 778

Text #18

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1126527 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3849. Min Act: -0.0000

Data Index: 761751 (The Pile)

Max Activating Token Index: 1006