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

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

Neuron 637 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1686. Min Act: -0.0001

Data Index: 496467 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1323. Min Act: -0.0002

Data Index: 787105 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1312. Min Act: -0.0002

Data Index: 624276 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1208. Min Act: -0.0002

Data Index: 770547 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1259. Min Act: -0.0002

Data Index: 1184319 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1277. Min Act: -0.0002

Data Index: 832831 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1270. Min Act: -0.0002

Data Index: 401057 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1212. Min Act: -0.0002

Data Index: 917283 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1303. Min Act: -0.0002

Data Index: 504974 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1205. Min Act: -0.0002

Data Index: 153539 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1229. Min Act: -0.0002

Data Index: 1359423 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1307. Min Act: -0.0002

Data Index: 539066 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1214. Min Act: -0.0002

Data Index: 1185997 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1219. Min Act: -0.0002

Data Index: 388930 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1199. Min Act: -0.0002

Data Index: 910028 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1200. Min Act: -0.0002

Data Index: 174398 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1157. Min Act: -0.0002

Data Index: 973156 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1149. Min Act: -0.0002

Data Index: 613516 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1184. Min Act: -0.0002

Data Index: 327676 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1190. Min Act: -0.0002

Data Index: 1155774 (C4 (Web Text))

Max Activating Token Index: 732