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

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

Neuron 460 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1124975 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2100. Min Act: -0.0000

Data Index: 101780 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2032. Min Act: -0.0000

Data Index: 719535 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2099. Min Act: -0.0000

Data Index: 635400 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2015. Min Act: -0.0000

Data Index: 147052 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1148255 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2012. Min Act: -0.0000

Data Index: 242225 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1810. Min Act: -0.0000

Data Index: 541339 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1926. Min Act: -0.0000

Data Index: 795287 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1789. Min Act: -0.0000

Data Index: 599776 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1221422 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1733. Min Act: -0.0000

Data Index: 28105 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1763. Min Act: -0.0000

Data Index: 1224662 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1726. Min Act: -0.0000

Data Index: 80932 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1719. Min Act: -0.0000

Data Index: 660504 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1783. Min Act: -0.0000

Data Index: 911809 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1660. Min Act: -0.0000

Data Index: 398468 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1644. Min Act: -0.0000

Data Index: 980648 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1578. Min Act: -0.0000

Data Index: 226725 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1684. Min Act: -0.0000

Data Index: 1295516 (C4 (Web Text))

Max Activating Token Index: 500