Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1196 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.7697. Min Act: -0.0001

Data Index: 223975 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 3.0038. Min Range: -3.0038

Max Act: 3.0038. Min Act: -0.0001

Data Index: 141436 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.3941. Min Act: -0.0001

Data Index: 753077 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.3864. Min Act: -0.0001

Data Index: 31298 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.6277. Min Act: -0.0001

Data Index: 982854 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 3.0038. Min Range: -3.0038

Max Act: 1.9746. Min Act: -0.0001

Data Index: 463817 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.7637. Min Act: -0.0001

Data Index: 1076608 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.4229. Min Act: -0.0001

Data Index: 739469 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.7300. Min Act: -0.0001

Data Index: 339525 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 3.0038. Min Range: -3.0038

Max Act: 1.8201. Min Act: -0.0001

Data Index: 1224449 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.8161. Min Act: -0.0001

Data Index: 206568 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.4048. Min Act: -0.0001

Data Index: 645248 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.4121. Min Act: -0.0001

Data Index: 1307212 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.4678. Min Act: -0.0001

Data Index: 1128737 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.4373. Min Act: -0.0001

Data Index: 1303944 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.3515. Min Act: -0.0001

Data Index: 53928 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.4934. Min Act: -0.0001

Data Index: 481087 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.2684. Min Act: -0.0001

Data Index: 261619 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.0019. Min Act: -0.0001

Data Index: 1205395 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 3.0038. Min Range: -3.0038

Max Act: 2.3378. Min Act: -0.0001

Data Index: 527318 (C4 (Web Text))

Max Activating Token Index: 727