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

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

Neuron 2240 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.7478. Min Act: -0.0000

Data Index: 79052 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.7270. Min Act: -0.0000

Data Index: 1226889 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.6969. Min Act: -0.0000

Data Index: 319107 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.6510. Min Act: -0.0000

Data Index: 951709 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.4863. Min Act: -0.0000

Data Index: 303955 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.5819. Min Act: -0.0000

Data Index: 770990 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.4390. Min Act: -0.0000

Data Index: 228844 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.5050. Min Act: -0.0000

Data Index: 310685 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.4075. Min Act: -0.0000

Data Index: 1082535 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.4003. Min Act: -0.0000

Data Index: 1278157 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.3443. Min Act: -0.0000

Data Index: 269955 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.2641. Min Act: -0.0000

Data Index: 122911 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.2107. Min Act: 0.0000

Data Index: 167798 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.2718. Min Act: -0.0000

Data Index: 727697 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.3445. Min Act: -0.0000

Data Index: 1298855 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.2668. Min Act: -0.0000

Data Index: 224600 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.2327. Min Act: -0.0000

Data Index: 1246884 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.2088. Min Act: -0.0000

Data Index: 1036231 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.2651. Min Act: -0.0000

Data Index: 863592 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 1.7478. Min Range: -1.7478

Max Act: 1.2019. Min Act: -0.0000

Data Index: 57269 (C4 (Web Text))

Max Activating Token Index: 660