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

Dataset: The Pile

Neuron 1703 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: 1.4270. Min Range: -1.4270

Max Act: 1.3680. Min Act: -0.0000

Data Index: 509441 (The Pile)

Max Activating Token Index: 998

Text #1

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.4021. Min Act: -0.0000

Data Index: 452390 (The Pile)

Max Activating Token Index: 476

Text #2

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.4270. Min Act: -0.0000

Data Index: 838451 (The Pile)

Max Activating Token Index: 571

Text #3

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.2768. Min Act: -0.0000

Data Index: 585841 (The Pile)

Max Activating Token Index: 460

Text #4

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.2633. Min Act: -0.0000

Data Index: 334302 (The Pile)

Max Activating Token Index: 195

Text #5

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.1858. Min Act: -0.0000

Data Index: 303962 (The Pile)

Max Activating Token Index: 362

Text #6

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.1888. Min Act: -0.0000

Data Index: 775939 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.1327. Min Act: -0.0000

Data Index: 688026 (The Pile)

Max Activating Token Index: 758

Text #8

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.0641. Min Act: -0.0000

Data Index: 190745 (The Pile)

Max Activating Token Index: 79

Text #9

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.0348. Min Act: -0.0000

Data Index: 1539776 (The Pile)

Max Activating Token Index: 30

Text #10

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.0814. Min Act: -0.0000

Data Index: 1522651 (The Pile)

Max Activating Token Index: 102

Text #11

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.1064. Min Act: -0.0000

Data Index: 222715 (The Pile)

Max Activating Token Index: 128

Text #12

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1078468 (The Pile)

Max Activating Token Index: 737

Text #13

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.0227. Min Act: -0.0000

Data Index: 890035 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.0248. Min Act: -0.0000

Data Index: 1420829 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1753723 (The Pile)

Max Activating Token Index: 994

Text #16

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.0388. Min Act: -0.0000

Data Index: 809372 (The Pile)

Max Activating Token Index: 751

Text #17

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.0309. Min Act: -0.0000

Data Index: 960914 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.0312. Min Act: -0.0000

Data Index: 1093500 (The Pile)

Max Activating Token Index: 546

Text #19

Max Range: 1.4270. Min Range: -1.4270

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1103008 (The Pile)

Max Activating Token Index: 100