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

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

Neuron 2087 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.4241. Min Act: -0.0000

Data Index: 931949 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.4211. Min Act: -0.0000

Data Index: 296877 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3661. Min Act: -0.0000

Data Index: 1017713 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3218. Min Act: -0.0000

Data Index: 864841 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3178. Min Act: -0.0000

Data Index: 898599 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1110720 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1153007 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.2857. Min Act: -0.0000

Data Index: 305215 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1225272 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1299132 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.2865. Min Act: -0.0000

Data Index: 585268 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.2920. Min Act: -0.0000

Data Index: 417746 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.2815. Min Act: -0.0000

Data Index: 590562 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1149075 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.2753. Min Act: -0.0000

Data Index: 968678 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.2832. Min Act: -0.0000

Data Index: 522032 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.2705. Min Act: -0.0000

Data Index: 570529 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.2741. Min Act: -0.0000

Data Index: 989081 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.2714. Min Act: -0.0000

Data Index: 974941 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.2573. Min Act: -0.0000

Data Index: 575475 (C4 (Web Text))

Max Activating Token Index: 901