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

Dataset: The Pile

Neuron 3454 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: 0.7511. Min Range: -0.7511

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1617484 (The Pile)

Max Activating Token Index: 556

Text #1

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6737. Min Act: -0.0000

Data Index: 12683 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6463. Min Act: -0.0000

Data Index: 472807 (The Pile)

Max Activating Token Index: 225

Text #3

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6237. Min Act: -0.0000

Data Index: 409584 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6202. Min Act: -0.0000

Data Index: 743729 (The Pile)

Max Activating Token Index: 304

Text #5

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6136. Min Act: -0.0000

Data Index: 638647 (The Pile)

Max Activating Token Index: 453

Text #6

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1115427 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1150296 (The Pile)

Max Activating Token Index: 425

Text #8

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6114. Min Act: -0.0000

Data Index: 444824 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1381197 (The Pile)

Max Activating Token Index: 112

Text #10

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1546295 (The Pile)

Max Activating Token Index: 752

Text #11

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1879047 (The Pile)

Max Activating Token Index: 103

Text #12

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1347769 (The Pile)

Max Activating Token Index: 659

Text #13

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1430583 (The Pile)

Max Activating Token Index: 805

Text #14

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1642353 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.5512. Min Act: -0.0000

Data Index: 750075 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1174556 (The Pile)

Max Activating Token Index: 978

Text #17

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1512755 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.5339. Min Act: -0.0000

Data Index: 892520 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.5781. Min Act: -0.0000

Data Index: 9650 (The Pile)

Max Activating Token Index: 575