Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1401 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.6029. Min Range: -3.6029

Max Act: 3.6029. Min Act: -0.0000

Data Index: 966679 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 3.6029. Min Range: -3.6029

Max Act: 3.5342. Min Act: -0.0000

Data Index: 15582 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 3.6029. Min Range: -3.6029

Max Act: 3.1117. Min Act: -0.0000

Data Index: 870869 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 3.6029. Min Range: -3.6029

Max Act: 3.1177. Min Act: -0.0000

Data Index: 1125728 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 3.6029. Min Range: -3.6029

Max Act: 3.0387. Min Act: -0.0000

Data Index: 904784 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.8677. Min Act: -0.0000

Data Index: 242191 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.6372. Min Act: -0.0000

Data Index: 884925 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.9020. Min Act: -0.0000

Data Index: 1000043 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.5592. Min Act: -0.0000

Data Index: 1291583 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.5218. Min Act: -0.0000

Data Index: 100048 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.5188. Min Act: -0.0000

Data Index: 169893 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.4023. Min Act: -0.0000

Data Index: 748203 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.5152. Min Act: -0.0000

Data Index: 387977 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.5126. Min Act: -0.0000

Data Index: 525146 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.4786. Min Act: -0.0000

Data Index: 913842 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.4729. Min Act: -0.0000

Data Index: 1342838 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.4884. Min Act: -0.0000

Data Index: 482152 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.2535. Min Act: -0.0000

Data Index: 529974 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.5132. Min Act: -0.0000

Data Index: 1039946 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.3606. Min Act: -0.0000

Data Index: 368594 (C4 (Web Text))

Max Activating Token Index: 324