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

Dataset: The Pile

Neuron 3530 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1146. Min Act: -0.0000

Data Index: 170158 (The Pile)

Max Activating Token Index: 755

Text #1

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1223. Min Act: -0.0000

Data Index: 1297189 (The Pile)

Max Activating Token Index: 513

Text #2

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1132196 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1020. Min Act: -0.0000

Data Index: 78234 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1049. Min Act: -0.0000

Data Index: 459661 (The Pile)

Max Activating Token Index: 428

Text #5

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1075. Min Act: -0.0000

Data Index: 674359 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1953011 (The Pile)

Max Activating Token Index: 658

Text #7

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0966. Min Act: -0.0000

Data Index: 3673 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1382097 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0939. Min Act: -0.0000

Data Index: 572913 (The Pile)

Max Activating Token Index: 727

Text #10

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0899. Min Act: -0.0000

Data Index: 811136 (The Pile)

Max Activating Token Index: 197

Text #11

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0895. Min Act: -0.0000

Data Index: 209189 (The Pile)

Max Activating Token Index: 588

Text #12

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1830338 (The Pile)

Max Activating Token Index: 918

Text #13

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0873. Min Act: -0.0000

Data Index: 300725 (The Pile)

Max Activating Token Index: 678

Text #14

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0902. Min Act: -0.0000

Data Index: 192741 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0924. Min Act: -0.0000

Data Index: 171001 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0901. Min Act: -0.0000

Data Index: 963349 (The Pile)

Max Activating Token Index: 652

Text #17

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0805. Min Act: -0.0000

Data Index: 824880 (The Pile)

Max Activating Token Index: 922

Text #18

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0888. Min Act: 0.0000

Data Index: 1997054 (The Pile)

Max Activating Token Index: 721

Text #19

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0855. Min Act: -0.0000

Data Index: 648407 (The Pile)

Max Activating Token Index: 850