Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 866 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.9171. Min Act: -0.0005

Data Index: 852172 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.6720. Min Act: -0.0005

Data Index: 980156 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.6154. Min Act: -0.0005

Data Index: 533365 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.5597. Min Act: -0.0005

Data Index: 755996 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.5600. Min Act: -0.0005

Data Index: 516151 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.5843. Min Act: -0.0005

Data Index: 265702 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.5602. Min Act: -0.0005

Data Index: 69634 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.5549. Min Act: -0.0005

Data Index: 561848 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.5432. Min Act: -0.0005

Data Index: 749649 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.5552. Min Act: -0.0005

Data Index: 264142 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.6112. Min Act: -0.0005

Data Index: 948085 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.5489. Min Act: -0.0005

Data Index: 196475 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.5054. Min Act: -0.0005

Data Index: 146441 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.5466. Min Act: -0.0005

Data Index: 294622 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.4937. Min Act: -0.0005

Data Index: 943667 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.4901. Min Act: -0.0005

Data Index: 859449 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.5239. Min Act: -0.0005

Data Index: 1344436 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.4878. Min Act: -0.0005

Data Index: 252498 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.5037. Min Act: -0.0005

Data Index: 732230 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.5013. Min Act: -0.0005

Data Index: 875009 (C4 (Web Text))

Max Activating Token Index: 543