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

Dataset: The Pile

Neuron 4554 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: 0.1719. Min Range: -0.1719

Max Act: 0.1719. Min Act: -0.0000

Data Index: 42549 (The Pile)

Max Activating Token Index: 789

Text #1

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1354. Min Act: -0.0000

Data Index: 353564 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1566985 (The Pile)

Max Activating Token Index: 433

Text #3

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1250. Min Act: -0.0000

Data Index: 542214 (The Pile)

Max Activating Token Index: 526

Text #4

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1256. Min Act: -0.0000

Data Index: 785162 (The Pile)

Max Activating Token Index: 938

Text #5

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1003407 (The Pile)

Max Activating Token Index: 494

Text #6

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1209. Min Act: -0.0000

Data Index: 944845 (The Pile)

Max Activating Token Index: 920

Text #7

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1107. Min Act: -0.0000

Data Index: 1295999 (The Pile)

Max Activating Token Index: 794

Text #8

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1151. Min Act: -0.0000

Data Index: 399555 (The Pile)

Max Activating Token Index: 484

Text #9

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1177. Min Act: 0.0000

Data Index: 394990 (The Pile)

Max Activating Token Index: 779

Text #10

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1069219 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1236. Min Act: -0.0000

Data Index: 642226 (The Pile)

Max Activating Token Index: 304

Text #12

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1343316 (The Pile)

Max Activating Token Index: 948

Text #13

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1002. Min Act: 0.0000

Data Index: 492027 (The Pile)

Max Activating Token Index: 779

Text #14

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1069. Min Act: -0.0000

Data Index: 912423 (The Pile)

Max Activating Token Index: 817

Text #15

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1057. Min Act: -0.0000

Data Index: 16365 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1899821 (The Pile)

Max Activating Token Index: 852

Text #17

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.0981. Min Act: 0.0000

Data Index: 1247825 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.0983. Min Act: -0.0000

Data Index: 68637 (The Pile)

Max Activating Token Index: 434

Text #19

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1001. Min Act: -0.0000

Data Index: 849384 (The Pile)

Max Activating Token Index: 818