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

Dataset: The Pile

Neuron 4494 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: 1.9578. Min Range: -1.9578

Max Act: 1.9578. Min Act: -0.0000

Data Index: 1617320 (The Pile)

Max Activating Token Index: 903

Text #1

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.8556. Min Act: -0.0000

Data Index: 878666 (The Pile)

Max Activating Token Index: 253

Text #2

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.8566. Min Act: -0.0000

Data Index: 1593060 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.7232. Min Act: -0.0000

Data Index: 1518783 (The Pile)

Max Activating Token Index: 12

Text #4

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.4809. Min Act: -0.0000

Data Index: 1457466 (The Pile)

Max Activating Token Index: 592

Text #5

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.6608. Min Act: -0.0000

Data Index: 1584989 (The Pile)

Max Activating Token Index: 15

Text #6

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.6592. Min Act: -0.0000

Data Index: 901998 (The Pile)

Max Activating Token Index: 849

Text #7

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.5452. Min Act: -0.0000

Data Index: 405431 (The Pile)

Max Activating Token Index: 901

Text #8

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.6001. Min Act: -0.0000

Data Index: 1512792 (The Pile)

Max Activating Token Index: 390

Text #9

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.6161. Min Act: -0.0000

Data Index: 595238 (The Pile)

Max Activating Token Index: 884

Text #10

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.5056. Min Act: -0.0000

Data Index: 1024607 (The Pile)

Max Activating Token Index: 18

Text #11

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.5791. Min Act: -0.0000

Data Index: 515595 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.5629. Min Act: -0.0000

Data Index: 1062595 (The Pile)

Max Activating Token Index: 501

Text #13

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.5114. Min Act: -0.0000

Data Index: 535723 (The Pile)

Max Activating Token Index: 32

Text #14

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.5333. Min Act: -0.0000

Data Index: 708045 (The Pile)

Max Activating Token Index: 566

Text #15

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.4148. Min Act: -0.0000

Data Index: 20777 (The Pile)

Max Activating Token Index: 558

Text #16

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.4494. Min Act: -0.0000

Data Index: 1580069 (The Pile)

Max Activating Token Index: 248

Text #17

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.6025. Min Act: -0.0000

Data Index: 719742 (The Pile)

Max Activating Token Index: 724

Text #18

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.4824. Min Act: -0.0000

Data Index: 1753003 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 1.9578. Min Range: -1.9578

Max Act: 1.4836. Min Act: -0.0000

Data Index: 1358754 (The Pile)

Max Activating Token Index: 278