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

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

Neuron 504 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1460. Min Act: -0.0002

Data Index: 469842 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1316. Min Act: -0.0002

Data Index: 1185497 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1355. Min Act: -0.0002

Data Index: 814847 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1245. Min Act: -0.0002

Data Index: 776251 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1367. Min Act: -0.0002

Data Index: 521369 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1224. Min Act: -0.0002

Data Index: 995171 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1258. Min Act: -0.0002

Data Index: 594302 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1221. Min Act: -0.0002

Data Index: 137168 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1165. Min Act: -0.0002

Data Index: 19120 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1194. Min Act: -0.0002

Data Index: 425581 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1172. Min Act: -0.0002

Data Index: 1107216 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1309. Min Act: -0.0002

Data Index: 377079 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1118. Min Act: -0.0002

Data Index: 1263109 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1109. Min Act: -0.0002

Data Index: 53115 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1199. Min Act: -0.0002

Data Index: 324787 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1111. Min Act: -0.0002

Data Index: 810180 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1106. Min Act: -0.0002

Data Index: 1222190 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1094. Min Act: -0.0002

Data Index: 48627 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1079. Min Act: -0.0002

Data Index: 845343 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1204. Min Act: -0.0002

Data Index: 5000 (C4 (Web Text))

Max Activating Token Index: 584