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

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

Neuron 475 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0320. Min Act: -0.0006

Data Index: 1267416 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1303272 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0315. Min Act: -0.0006

Data Index: 439893 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0321. Min Act: -0.0006

Data Index: 1122149 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0313. Min Act: -0.0006

Data Index: 937123 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0300. Min Act: -0.0006

Data Index: 937434 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0299. Min Act: -0.0006

Data Index: 502522 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0311. Min Act: -0.0006

Data Index: 1003073 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0308. Min Act: -0.0006

Data Index: 639021 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0294. Min Act: -0.0006

Data Index: 1166256 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0286. Min Act: -0.0006

Data Index: 766813 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0286. Min Act: -0.0006

Data Index: 1181355 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0303. Min Act: -0.0006

Data Index: 661850 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0277. Min Act: -0.0006

Data Index: 513882 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0290. Min Act: -0.0006

Data Index: 1023973 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0283. Min Act: -0.0006

Data Index: 950461 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0265. Min Act: -0.0006

Data Index: 140221 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0266. Min Act: -0.0006

Data Index: 179504 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0264. Min Act: -0.0006

Data Index: 122230 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0282. Min Act: -0.0006

Data Index: 1325008 (C4 (Web Text))

Max Activating Token Index: 71