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

Dataset: The Pile

Neuron 1246 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: 1.9762. Min Range: -1.9762

Max Act: 1.9762. Min Act: -0.0000

Data Index: 372297 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.8806. Min Act: -0.0000

Data Index: 645296 (The Pile)

Max Activating Token Index: 145

Text #2

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9422. Min Act: -0.0000

Data Index: 1750207 (The Pile)

Max Activating Token Index: 420

Text #3

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.9203. Min Act: -0.0000

Data Index: 1590073 (The Pile)

Max Activating Token Index: 621

Text #4

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.8194. Min Act: -0.0000

Data Index: 845463 (The Pile)

Max Activating Token Index: 449

Text #5

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.6499. Min Act: -0.0000

Data Index: 1204771 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.6473. Min Act: -0.0000

Data Index: 1045238 (The Pile)

Max Activating Token Index: 803

Text #7

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.5203. Min Act: -0.0000

Data Index: 1732797 (The Pile)

Max Activating Token Index: 496

Text #8

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.5415. Min Act: -0.0000

Data Index: 1793372 (The Pile)

Max Activating Token Index: 414

Text #9

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.5050. Min Act: -0.0000

Data Index: 1556057 (The Pile)

Max Activating Token Index: 380

Text #10

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.4250. Min Act: -0.0000

Data Index: 1843536 (The Pile)

Max Activating Token Index: 217

Text #11

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.4074. Min Act: -0.0000

Data Index: 1223483 (The Pile)

Max Activating Token Index: 160

Text #12

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.3943. Min Act: -0.0000

Data Index: 1484801 (The Pile)

Max Activating Token Index: 899

Text #13

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.2247. Min Act: -0.0000

Data Index: 925894 (The Pile)

Max Activating Token Index: 153

Text #14

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.3600. Min Act: -0.0000

Data Index: 1237966 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.2828. Min Act: -0.0000

Data Index: 908447 (The Pile)

Max Activating Token Index: 674

Text #16

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.4332. Min Act: -0.0000

Data Index: 269807 (The Pile)

Max Activating Token Index: 455

Text #17

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.3963. Min Act: -0.0000

Data Index: 1071883 (The Pile)

Max Activating Token Index: 100

Text #18

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.3940. Min Act: -0.0000

Data Index: 1114361 (The Pile)

Max Activating Token Index: 1001

Text #19

Max Range: 1.9762. Min Range: -1.9762

Max Act: 1.2428. Min Act: -0.0000

Data Index: 1519955 (The Pile)

Max Activating Token Index: 290