Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1913 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.6122. Min Act: -0.0005

Data Index: 401378 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5419. Min Act: -0.0005

Data Index: 1294942 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5002. Min Act: -0.0005

Data Index: 321032 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4986. Min Act: -0.0005

Data Index: 751533 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4630. Min Act: -0.0006

Data Index: 355110 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4619. Min Act: -0.0005

Data Index: 1007763 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4599. Min Act: -0.0005

Data Index: 1224876 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4502. Min Act: -0.0005

Data Index: 913020 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4491. Min Act: -0.0005

Data Index: 1014715 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4496. Min Act: -0.0005

Data Index: 580803 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4625. Min Act: -0.0005

Data Index: 650217 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4460. Min Act: -0.0005

Data Index: 855925 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4565. Min Act: -0.0005

Data Index: 1272055 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4182. Min Act: -0.0005

Data Index: 1164180 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4325. Min Act: -0.0005

Data Index: 1109902 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4311. Min Act: -0.0005

Data Index: 443010 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4294. Min Act: -0.0005

Data Index: 244527 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4254. Min Act: -0.0005

Data Index: 94175 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4104. Min Act: -0.0006

Data Index: 1102238 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4085. Min Act: -0.0005

Data Index: 1219905 (C4 (Web Text))

Max Activating Token Index: 1023