Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 115 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0270. Min Act: -0.0006

Data Index: 852054 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0220. Min Act: -0.0006

Data Index: 1269644 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1099940 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0201. Min Act: -0.0006

Data Index: 747120 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1619757 (Python Code)

Max Activating Token Index: 898

Text #5

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0207. Min Act: -0.0006

Data Index: 602586 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1563021 (Python Code)

Max Activating Token Index: 237

Text #7

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0216. Min Act: -0.0006

Data Index: 1141755 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0219. Min Act: -0.0006

Data Index: 170078 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1020328 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1035220 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0212. Min Act: -0.0006

Data Index: 958735 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1127502 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0203. Min Act: -0.0006

Data Index: 1612929 (Python Code)

Max Activating Token Index: 877

Text #14

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0212. Min Act: -0.0006

Data Index: 291017 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0197. Min Act: -0.0006

Data Index: 463865 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0200. Min Act: -0.0006

Data Index: 960230 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1181245 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0209. Min Act: -0.0006

Data Index: 283383 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0208. Min Act: -0.0006

Data Index: 615786 (C4 (Web Text))

Max Activating Token Index: 231