Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2075 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1693. Min Act: -0.0001

Data Index: 653242 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1642. Min Act: -0.0001

Data Index: 1127850 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1623. Min Act: -0.0000

Data Index: 187501 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1221. Min Act: -0.0001

Data Index: 962306 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1009720 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1159. Min Act: -0.0000

Data Index: 767298 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1060. Min Act: -0.0000

Data Index: 324596 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1265149 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1070. Min Act: -0.0000

Data Index: 549188 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1061286 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1042. Min Act: -0.0000

Data Index: 774673 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1152234 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1014. Min Act: -0.0001

Data Index: 648535 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0966. Min Act: -0.0001

Data Index: 750258 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0984. Min Act: -0.0000

Data Index: 327132 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1165403 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0942. Min Act: -0.0001

Data Index: 71691 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0972. Min Act: -0.0001

Data Index: 797669 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0917. Min Act: -0.0000

Data Index: 552758 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0875. Min Act: -0.0000

Data Index: 957799 (C4 (Web Text))

Max Activating Token Index: 129