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

Dataset: The Pile

Neuron 1854 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.8867. Min Act: -0.0000

Data Index: 309336 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.8008. Min Act: -0.0000

Data Index: 674101 (The Pile)

Max Activating Token Index: 928

Text #2

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1806837 (The Pile)

Max Activating Token Index: 1002

Text #3

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.6771. Min Act: -0.0000

Data Index: 230542 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1259847 (The Pile)

Max Activating Token Index: 572

Text #5

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.6999. Min Act: -0.0000

Data Index: 1083655 (The Pile)

Max Activating Token Index: 62

Text #6

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1644357 (The Pile)

Max Activating Token Index: 688

Text #7

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.7519. Min Act: -0.0000

Data Index: 542955 (The Pile)

Max Activating Token Index: 1007

Text #8

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1230347 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.5997. Min Act: -0.0000

Data Index: 828986 (The Pile)

Max Activating Token Index: 979

Text #10

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1955154 (The Pile)

Max Activating Token Index: 726

Text #11

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1712630 (The Pile)

Max Activating Token Index: 541

Text #12

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1329617 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.5704. Min Act: -0.0000

Data Index: 943987 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.5443. Min Act: -0.0000

Data Index: 768451 (The Pile)

Max Activating Token Index: 734

Text #15

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.6622. Min Act: -0.0000

Data Index: 544494 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1419081 (The Pile)

Max Activating Token Index: 336

Text #17

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.6305. Min Act: -0.0000

Data Index: 611593 (The Pile)

Max Activating Token Index: 948

Text #18

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1652526 (The Pile)

Max Activating Token Index: 860

Text #19

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.6137. Min Act: -0.0000

Data Index: 817685 (The Pile)

Max Activating Token Index: 165