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

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

Neuron 502 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3884. Min Act: -0.0002

Data Index: 891571 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.4102. Min Act: -0.0002

Data Index: 33167 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.4134. Min Act: -0.0002

Data Index: 5931 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3599. Min Act: -0.0002

Data Index: 1324406 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3366. Min Act: -0.0002

Data Index: 735703 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3281. Min Act: -0.0002

Data Index: 1209796 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3336. Min Act: -0.0002

Data Index: 1241704 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3127. Min Act: -0.0002

Data Index: 1220955 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3333. Min Act: -0.0002

Data Index: 702478 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3060. Min Act: -0.0002

Data Index: 731161 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3304. Min Act: -0.0002

Data Index: 314471 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3437. Min Act: -0.0002

Data Index: 1012812 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2922. Min Act: -0.0002

Data Index: 176952 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2920. Min Act: -0.0002

Data Index: 1199507 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3069. Min Act: -0.0002

Data Index: 643848 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3049. Min Act: -0.0002

Data Index: 1193041 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3045. Min Act: -0.0002

Data Index: 355690 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3034. Min Act: -0.0002

Data Index: 5943 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2958. Min Act: -0.0002

Data Index: 494715 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2892. Min Act: -0.0002

Data Index: 662484 (C4 (Web Text))

Max Activating Token Index: 534