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

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

Neuron 4584 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2005. Min Range: -1.2005

Max Act: 1.2005. Min Act: -0.0000

Data Index: 1109440 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 1.2005. Min Range: -1.2005

Max Act: 1.0529. Min Act: -0.0000

Data Index: 41331 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 1.2005. Min Range: -1.2005

Max Act: 1.0620. Min Act: -0.0000

Data Index: 154737 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 1.2005. Min Range: -1.2005

Max Act: 1.0870. Min Act: -0.0001

Data Index: 833503 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 1.2005. Min Range: -1.2005

Max Act: 1.0161. Min Act: -0.0001

Data Index: 1199950 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9167. Min Act: -0.0000

Data Index: 69630 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9612. Min Act: -0.0000

Data Index: 9742 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1182941 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9762. Min Act: -0.0001

Data Index: 748339 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9569. Min Act: -0.0000

Data Index: 537526 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9064. Min Act: -0.0001

Data Index: 1231216 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9187. Min Act: -0.0000

Data Index: 14430 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9144. Min Act: -0.0000

Data Index: 626299 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9116. Min Act: -0.0000

Data Index: 487362 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.8927. Min Act: -0.0000

Data Index: 797409 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.8927. Min Act: -0.0000

Data Index: 181834 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.8542. Min Act: -0.0000

Data Index: 755079 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.8767. Min Act: -0.0000

Data Index: 964758 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9035. Min Act: -0.0000

Data Index: 356293 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1190095 (C4 (Web Text))

Max Activating Token Index: 53