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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1910 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8015. Min Range: -1.8015

Max Act: 1.8015. Min Act: -0.0000

Data Index: 520688 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 1.8015. Min Range: -1.8015

Max Act: 1.4214. Min Act: -0.0001

Data Index: 243052 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 1.8015. Min Range: -1.8015

Max Act: 1.5636. Min Act: -0.0001

Data Index: 787216 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 1.8015. Min Range: -1.8015

Max Act: 1.1697. Min Act: -0.0000

Data Index: 418146 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 1.8015. Min Range: -1.8015

Max Act: 1.2403. Min Act: -0.0000

Data Index: 1172128 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 1.8015. Min Range: -1.8015

Max Act: 1.0668. Min Act: -0.0001

Data Index: 643746 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 1.8015. Min Range: -1.8015

Max Act: 0.9932. Min Act: -0.0001

Data Index: 1275189 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 1.8015. Min Range: -1.8015

Max Act: 1.0419. Min Act: -0.0001

Data Index: 26209 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 1.8015. Min Range: -1.8015

Max Act: 0.9692. Min Act: -0.0001

Data Index: 782708 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 1.8015. Min Range: -1.8015

Max Act: 1.0134. Min Act: -0.0000

Data Index: 553824 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 1.8015. Min Range: -1.8015

Max Act: 1.0827. Min Act: -0.0000

Data Index: 457996 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 1.8015. Min Range: -1.8015

Max Act: 1.0099. Min Act: -0.0000

Data Index: 863153 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 1.8015. Min Range: -1.8015

Max Act: 0.9699. Min Act: -0.0001

Data Index: 1091484 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 1.8015. Min Range: -1.8015

Max Act: 1.0003. Min Act: -0.0000

Data Index: 1024693 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 1.8015. Min Range: -1.8015

Max Act: 0.9089. Min Act: -0.0000

Data Index: 966079 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 1.8015. Min Range: -1.8015

Max Act: 0.9867. Min Act: -0.0001

Data Index: 911214 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 1.8015. Min Range: -1.8015

Max Act: 0.8986. Min Act: -0.0001

Data Index: 1351610 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 1.8015. Min Range: -1.8015

Max Act: 0.9477. Min Act: -0.0000

Data Index: 358565 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 1.8015. Min Range: -1.8015

Max Act: 0.9159. Min Act: -0.0000

Data Index: 1039187 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 1.8015. Min Range: -1.8015

Max Act: 0.9674. Min Act: -0.0000

Data Index: 964370 (C4 (Web Text))

Max Activating Token Index: 10