Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5268 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0312. Min Act: -0.0001

Data Index: 884508 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1153013 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0265. Min Act: -0.0001

Data Index: 247607 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0249. Min Act: -0.0001

Data Index: 1265628 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0236. Min Act: -0.0001

Data Index: 1339597 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0242. Min Act: -0.0001

Data Index: 815555 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0215. Min Act: -0.0001

Data Index: 389216 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1109799 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0220. Min Act: -0.0001

Data Index: 1415058 (Python Code)

Max Activating Token Index: 244

Text #9

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0215. Min Act: -0.0001

Data Index: 831965 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0229. Min Act: -0.0001

Data Index: 838691 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0199. Min Act: -0.0001

Data Index: 1628053 (Python Code)

Max Activating Token Index: 76

Text #12

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0218. Min Act: -0.0001

Data Index: 687285 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0210. Min Act: -0.0001

Data Index: 870038 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0212. Min Act: -0.0001

Data Index: 195141 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0203. Min Act: -0.0001

Data Index: 689255 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1429926 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0204. Min Act: -0.0001

Data Index: 841137 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1274190 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0186. Min Act: -0.0001

Data Index: 1640006 (Python Code)

Max Activating Token Index: 357