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

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

Neuron 540 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: 0.0310. Min Range: -0.0310

Max Act: 0.0302. Min Act: -0.0006

Data Index: 844266 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0310. Min Act: -0.0006

Data Index: 431074 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0302. Min Act: -0.0006

Data Index: 239870 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0300. Min Act: -0.0006

Data Index: 1290673 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0299. Min Act: -0.0006

Data Index: 747303 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0290. Min Act: -0.0006

Data Index: 1204778 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0291. Min Act: -0.0006

Data Index: 838742 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0274. Min Act: -0.0006

Data Index: 15890 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0286. Min Act: -0.0006

Data Index: 1280763 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0282. Min Act: -0.0006

Data Index: 547275 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0270. Min Act: -0.0006

Data Index: 38490 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0270. Min Act: -0.0006

Data Index: 777586 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0257. Min Act: -0.0006

Data Index: 280090 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0261. Min Act: -0.0006

Data Index: 360238 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0266. Min Act: -0.0006

Data Index: 690128 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0266. Min Act: -0.0006

Data Index: 1158364 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0264. Min Act: -0.0006

Data Index: 1132430 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0282. Min Act: -0.0006

Data Index: 579723 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0276. Min Act: -0.0006

Data Index: 667395 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0264. Min Act: -0.0006

Data Index: 1268521 (C4 (Web Text))

Max Activating Token Index: 36