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

Dataset: The Pile

Neuron 4702 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4578. Min Range: -1.4578

Max Act: 1.4578. Min Act: -0.0000

Data Index: 1185668 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 1.4578. Min Range: -1.4578

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1924766 (The Pile)

Max Activating Token Index: 76

Text #2

Max Range: 1.4578. Min Range: -1.4578

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1257583 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.9789. Min Act: -0.0000

Data Index: 94644 (The Pile)

Max Activating Token Index: 232

Text #4

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.9425. Min Act: -0.0000

Data Index: 1977903 (The Pile)

Max Activating Token Index: 1006

Text #5

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.9523. Min Act: -0.0000

Data Index: 1107444 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.9254. Min Act: -0.0000

Data Index: 815037 (The Pile)

Max Activating Token Index: 609

Text #7

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.8728. Min Act: -0.0000

Data Index: 295517 (The Pile)

Max Activating Token Index: 23

Text #8

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.9087. Min Act: -0.0000

Data Index: 52096 (The Pile)

Max Activating Token Index: 925

Text #9

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.8541. Min Act: -0.0000

Data Index: 430238 (The Pile)

Max Activating Token Index: 341

Text #10

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.9421. Min Act: -0.0000

Data Index: 1379203 (The Pile)

Max Activating Token Index: 859

Text #11

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.8767. Min Act: -0.0000

Data Index: 690866 (The Pile)

Max Activating Token Index: 449

Text #12

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1545245 (The Pile)

Max Activating Token Index: 123

Text #13

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.8939. Min Act: -0.0000

Data Index: 755178 (The Pile)

Max Activating Token Index: 266

Text #14

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.8398. Min Act: -0.0000

Data Index: 336775 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.8775. Min Act: -0.0000

Data Index: 635710 (The Pile)

Max Activating Token Index: 159

Text #16

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.9120. Min Act: -0.0000

Data Index: 1937451 (The Pile)

Max Activating Token Index: 215

Text #17

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1682454 (The Pile)

Max Activating Token Index: 157

Text #18

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1358781 (The Pile)

Max Activating Token Index: 932

Text #19

Max Range: 1.4578. Min Range: -1.4578

Max Act: 0.9239. Min Act: -0.0000

Data Index: 816726 (The Pile)

Max Activating Token Index: 902