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

Dataset: The Pile

Neuron 685 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.5822. Min Act: -0.0000

Data Index: 997184 (The Pile)

Max Activating Token Index: 72

Text #1

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.4533. Min Act: -0.0000

Data Index: 292675 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.3096. Min Act: -0.0000

Data Index: 984248 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1420140 (The Pile)

Max Activating Token Index: 165

Text #4

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.3152. Min Act: -0.0000

Data Index: 1472555 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1462602 (The Pile)

Max Activating Token Index: 289

Text #6

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.2737. Min Act: -0.0000

Data Index: 670670 (The Pile)

Max Activating Token Index: 509

Text #7

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.3000. Min Act: -0.0000

Data Index: 181705 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.3146. Min Act: -0.0000

Data Index: 616159 (The Pile)

Max Activating Token Index: 666

Text #9

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.2859. Min Act: -0.0001

Data Index: 1521266 (The Pile)

Max Activating Token Index: 785

Text #10

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.2710. Min Act: -0.0000

Data Index: 789176 (The Pile)

Max Activating Token Index: 570

Text #11

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.2994. Min Act: -0.0000

Data Index: 1290683 (The Pile)

Max Activating Token Index: 522

Text #12

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1957400 (The Pile)

Max Activating Token Index: 528

Text #13

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.2660. Min Act: -0.0000

Data Index: 44685 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.2405. Min Act: -0.0000

Data Index: 680276 (The Pile)

Max Activating Token Index: 73

Text #15

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.2654. Min Act: -0.0000

Data Index: 119221 (The Pile)

Max Activating Token Index: 822

Text #16

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.2834. Min Act: -0.0000

Data Index: 407914 (The Pile)

Max Activating Token Index: 905

Text #17

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1127771 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1754284 (The Pile)

Max Activating Token Index: 781

Text #19

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.2462. Min Act: -0.0000

Data Index: 128248 (The Pile)

Max Activating Token Index: 329