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

Dataset: The Pile

Neuron 4048 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0787. Min Act: 0.0000

Data Index: 174617 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0786. Min Act: 0.0000

Data Index: 1339876 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0785. Min Act: 0.0000

Data Index: 1156597 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0742. Min Act: 0.0000

Data Index: 1965371 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1110209 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0725. Min Act: -0.0000

Data Index: 869588 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0627. Min Act: -0.0000

Data Index: 1815770 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0621. Min Act: -0.0001

Data Index: 482053 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1440088 (The Pile)

Max Activating Token Index: 934

Text #9

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1107832 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0467. Min Act: -0.0000

Data Index: 1865513 (The Pile)

Max Activating Token Index: 848

Text #11

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0511. Min Act: -0.0000

Data Index: 893782 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1442628 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0491. Min Act: -0.0000

Data Index: 670187 (The Pile)

Max Activating Token Index: 912

Text #14

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0483. Min Act: -0.0000

Data Index: 909404 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0458. Min Act: -0.0000

Data Index: 518075 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0460. Min Act: -0.0001

Data Index: 1745495 (The Pile)

Max Activating Token Index: 1003

Text #17

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0471. Min Act: 0.0000

Data Index: 900741 (The Pile)

Max Activating Token Index: 981

Text #18

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0465. Min Act: -0.0000

Data Index: 288642 (The Pile)

Max Activating Token Index: 979

Text #19

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0460. Min Act: -0.0000

Data Index: 448021 (The Pile)

Max Activating Token Index: 969