Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 512 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1506. Min Act: -0.0002

Data Index: 1328044 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1453. Min Act: -0.0001

Data Index: 42513 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1368. Min Act: -0.0002

Data Index: 1055892 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1330. Min Act: -0.0002

Data Index: 819802 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1275. Min Act: -0.0001

Data Index: 925438 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1263. Min Act: -0.0002

Data Index: 1035648 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1267. Min Act: -0.0002

Data Index: 735797 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1284. Min Act: -0.0001

Data Index: 851206 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1260. Min Act: -0.0002

Data Index: 1142239 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1215. Min Act: -0.0002

Data Index: 319294 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1191. Min Act: -0.0002

Data Index: 82196 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1203. Min Act: -0.0001

Data Index: 626890 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1121. Min Act: -0.0001

Data Index: 50317 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1186. Min Act: -0.0001

Data Index: 110826 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1147. Min Act: -0.0002

Data Index: 359289 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1163. Min Act: -0.0001

Data Index: 310150 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1113171 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1169. Min Act: -0.0002

Data Index: 1245165 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1109. Min Act: -0.0001

Data Index: 548123 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1108. Min Act: -0.0001

Data Index: 274848 (C4 (Web Text))

Max Activating Token Index: 594