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

Dataset: The Pile

Neuron 3809 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: 2.2555. Min Range: -2.2555

Max Act: 2.2555. Min Act: -0.0001

Data Index: 1249308 (The Pile)

Max Activating Token Index: 495

Text #1

Max Range: 2.2555. Min Range: -2.2555

Max Act: 2.0272. Min Act: -0.0000

Data Index: 374885 (The Pile)

Max Activating Token Index: 758

Text #2

Max Range: 2.2555. Min Range: -2.2555

Max Act: 2.1318. Min Act: -0.0000

Data Index: 718227 (The Pile)

Max Activating Token Index: 544

Text #3

Max Range: 2.2555. Min Range: -2.2555

Max Act: 1.7282. Min Act: -0.0000

Data Index: 1103224 (The Pile)

Max Activating Token Index: 851

Text #4

Max Range: 2.2555. Min Range: -2.2555

Max Act: 2.1850. Min Act: -0.0000

Data Index: 1071313 (The Pile)

Max Activating Token Index: 9

Text #5

Max Range: 2.2555. Min Range: -2.2555

Max Act: 1.8561. Min Act: -0.0000

Data Index: 369730 (The Pile)

Max Activating Token Index: 615

Text #6

Max Range: 2.2555. Min Range: -2.2555

Max Act: 1.6043. Min Act: -0.0000

Data Index: 1842119 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 2.2555. Min Range: -2.2555

Max Act: 2.0180. Min Act: -0.0000

Data Index: 280272 (The Pile)

Max Activating Token Index: 481

Text #8

Max Range: 2.2555. Min Range: -2.2555

Max Act: 1.9033. Min Act: -0.0001

Data Index: 756424 (The Pile)

Max Activating Token Index: 602

Text #9

Max Range: 2.2555. Min Range: -2.2555

Max Act: 2.1072. Min Act: -0.0000

Data Index: 151837 (The Pile)

Max Activating Token Index: 23

Text #10

Max Range: 2.2555. Min Range: -2.2555

Max Act: 1.8942. Min Act: -0.0000

Data Index: 321174 (The Pile)

Max Activating Token Index: 286

Text #11

Max Range: 2.2555. Min Range: -2.2555

Max Act: 2.0065. Min Act: -0.0000

Data Index: 1405452 (The Pile)

Max Activating Token Index: 296

Text #12

Max Range: 2.2555. Min Range: -2.2555

Max Act: 1.8114. Min Act: -0.0000

Data Index: 40205 (The Pile)

Max Activating Token Index: 655

Text #13

Max Range: 2.2555. Min Range: -2.2555

Max Act: 1.9099. Min Act: -0.0000

Data Index: 859356 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 2.2555. Min Range: -2.2555

Max Act: 1.9749. Min Act: -0.0000

Data Index: 1154595 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 2.2555. Min Range: -2.2555

Max Act: 1.7872. Min Act: -0.0000

Data Index: 294436 (The Pile)

Max Activating Token Index: 980

Text #16

Max Range: 2.2555. Min Range: -2.2555

Max Act: 1.9870. Min Act: -0.0000

Data Index: 1867533 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 2.2555. Min Range: -2.2555

Max Act: 1.8005. Min Act: -0.0000

Data Index: 371598 (The Pile)

Max Activating Token Index: 5

Text #18

Max Range: 2.2555. Min Range: -2.2555

Max Act: 1.8663. Min Act: -0.0001

Data Index: 902457 (The Pile)

Max Activating Token Index: 98

Text #19

Max Range: 2.2555. Min Range: -2.2555

Max Act: 2.0880. Min Act: -0.0000

Data Index: 27423 (The Pile)

Max Activating Token Index: 708