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

Dataset: The Pile

Neuron 1052 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: 0.4662. Min Range: -0.4662

Max Act: 0.4662. Min Act: -0.0000

Data Index: 365768 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3424. Min Act: -0.0000

Data Index: 1904146 (The Pile)

Max Activating Token Index: 588

Text #2

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3453. Min Act: -0.0000

Data Index: 121266 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3082. Min Act: -0.0000

Data Index: 558928 (The Pile)

Max Activating Token Index: 945

Text #4

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1043227 (The Pile)

Max Activating Token Index: 552

Text #5

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3329. Min Act: -0.0000

Data Index: 716318 (The Pile)

Max Activating Token Index: 398

Text #6

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3458. Min Act: -0.0000

Data Index: 844007 (The Pile)

Max Activating Token Index: 929

Text #7

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1261659 (The Pile)

Max Activating Token Index: 123

Text #8

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1418847 (The Pile)

Max Activating Token Index: 366

Text #9

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.2965. Min Act: -0.0000

Data Index: 330803 (The Pile)

Max Activating Token Index: 29

Text #10

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1396078 (The Pile)

Max Activating Token Index: 256

Text #11

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.2812. Min Act: -0.0000

Data Index: 6900 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3003. Min Act: -0.0000

Data Index: 588554 (The Pile)

Max Activating Token Index: 63

Text #13

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.2627. Min Act: -0.0000

Data Index: 520575 (The Pile)

Max Activating Token Index: 927

Text #14

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3017. Min Act: -0.0000

Data Index: 589542 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3085. Min Act: -0.0000

Data Index: 372726 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.2871. Min Act: -0.0000

Data Index: 1037839 (The Pile)

Max Activating Token Index: 609

Text #17

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1451845 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1702733 (The Pile)

Max Activating Token Index: 989

Text #19

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.2495. Min Act: -0.0000

Data Index: 232045 (The Pile)

Max Activating Token Index: 755