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

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

Neuron 1559 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0310. Min Act: -0.0005

Data Index: 795419 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0308. Min Act: -0.0005

Data Index: 635508 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0338. Min Act: -0.0005

Data Index: 742926 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0232. Min Act: -0.0005

Data Index: 1040909 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0254. Min Act: -0.0005

Data Index: 652698 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0312. Min Act: -0.0005

Data Index: 176140 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0293. Min Act: -0.0005

Data Index: 1246713 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0194. Min Act: -0.0005

Data Index: 879132 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0283. Min Act: -0.0005

Data Index: 1156976 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0285. Min Act: -0.0005

Data Index: 90390 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0184. Min Act: -0.0005

Data Index: 991570 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0269. Min Act: -0.0005

Data Index: 806215 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0291. Min Act: -0.0005

Data Index: 1065441 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0250. Min Act: -0.0005

Data Index: 1343264 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0264. Min Act: -0.0005

Data Index: 538434 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0249. Min Act: -0.0005

Data Index: 1086925 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0261. Min Act: -0.0005

Data Index: 1050778 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0274. Min Act: -0.0005

Data Index: 1343572 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0246. Min Act: -0.0005

Data Index: 553082 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0247. Min Act: -0.0005

Data Index: 877778 (C4 (Web Text))

Max Activating Token Index: 559