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

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

Neuron 1203 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5154. Min Range: -5.5154

Max Act: 5.5154. Min Act: -0.0000

Data Index: 1003051 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 5.5154. Min Range: -5.5154

Max Act: 5.1242. Min Act: -0.0000

Data Index: 717166 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 5.5154. Min Range: -5.5154

Max Act: 5.4593. Min Act: -0.0000

Data Index: 425167 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 5.5154. Min Range: -5.5154

Max Act: 4.9257. Min Act: -0.0000

Data Index: 1239143 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 5.5154. Min Range: -5.5154

Max Act: 5.4643. Min Act: -0.0000

Data Index: 851629 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 5.5154. Min Range: -5.5154

Max Act: 5.2772. Min Act: -0.0000

Data Index: 401383 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 5.5154. Min Range: -5.5154

Max Act: 5.0579. Min Act: -0.0000

Data Index: 914497 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 5.5154. Min Range: -5.5154

Max Act: 5.0650. Min Act: -0.0000

Data Index: 709510 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 5.5154. Min Range: -5.5154

Max Act: 5.1372. Min Act: -0.0000

Data Index: 593342 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 5.5154. Min Range: -5.5154

Max Act: 5.1119. Min Act: -0.0000

Data Index: 961333 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 5.5154. Min Range: -5.5154

Max Act: 5.2928. Min Act: -0.0000

Data Index: 1267377 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 5.5154. Min Range: -5.5154

Max Act: 5.0898. Min Act: -0.0000

Data Index: 1629 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 5.5154. Min Range: -5.5154

Max Act: 4.9745. Min Act: -0.0000

Data Index: 886701 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 5.5154. Min Range: -5.5154

Max Act: 4.8006. Min Act: -0.0000

Data Index: 1288887 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 5.5154. Min Range: -5.5154

Max Act: 4.7787. Min Act: -0.0000

Data Index: 207203 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 5.5154. Min Range: -5.5154

Max Act: 4.7735. Min Act: -0.0000

Data Index: 850841 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 5.5154. Min Range: -5.5154

Max Act: 4.9425. Min Act: -0.0000

Data Index: 321002 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 5.5154. Min Range: -5.5154

Max Act: 4.7652. Min Act: -0.0000

Data Index: 1187271 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 5.5154. Min Range: -5.5154

Max Act: 5.1007. Min Act: -0.0000

Data Index: 813093 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 5.5154. Min Range: -5.5154

Max Act: 4.8239. Min Act: -0.0000

Data Index: 145792 (C4 (Web Text))

Max Activating Token Index: 399