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

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

Neuron 3164 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1208. Min Act: -0.0001

Data Index: 127540 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1065. Min Act: -0.0001

Data Index: 523533 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1031. Min Act: -0.0001

Data Index: 921797 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1035. Min Act: -0.0001

Data Index: 698974 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1216 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1001. Min Act: -0.0001

Data Index: 373807 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0949. Min Act: -0.0001

Data Index: 432426 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0930. Min Act: -0.0001

Data Index: 610622 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1010. Min Act: -0.0001

Data Index: 722300 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0961. Min Act: -0.0001

Data Index: 215415 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0927. Min Act: -0.0001

Data Index: 577458 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0794. Min Act: -0.0001

Data Index: 1189820 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0905. Min Act: -0.0001

Data Index: 787513 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1296333 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0883. Min Act: -0.0001

Data Index: 427745 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0874. Min Act: -0.0001

Data Index: 371545 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1316041 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1244071 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1304065 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0872. Min Act: -0.0001

Data Index: 1127186 (C4 (Web Text))

Max Activating Token Index: 629