Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1511 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.8251. Min Range: -1.8251

Max Act: 1.8251. Min Act: -0.0001

Data Index: 504226 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 1.8251. Min Range: -1.8251

Max Act: 1.2872. Min Act: -0.0001

Data Index: 100893 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 1.8251. Min Range: -1.8251

Max Act: 1.2120. Min Act: -0.0001

Data Index: 615433 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 1.8251. Min Range: -1.8251

Max Act: 1.1701. Min Act: -0.0001

Data Index: 605681 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 1.8251. Min Range: -1.8251

Max Act: 1.1247. Min Act: -0.0001

Data Index: 559725 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 1.8251. Min Range: -1.8251

Max Act: 1.0484. Min Act: -0.0001

Data Index: 313699 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 1.8251. Min Range: -1.8251

Max Act: 1.0383. Min Act: -0.0001

Data Index: 759117 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 1.8251. Min Range: -1.8251

Max Act: 1.0158. Min Act: -0.0001

Data Index: 758391 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 1.8251. Min Range: -1.8251

Max Act: 1.0043. Min Act: -0.0001

Data Index: 1355329 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 1.8251. Min Range: -1.8251

Max Act: 0.9278. Min Act: -0.0001

Data Index: 830564 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 1.8251. Min Range: -1.8251

Max Act: 0.9289. Min Act: -0.0001

Data Index: 218859 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 1.8251. Min Range: -1.8251

Max Act: 1.0397. Min Act: -0.0001

Data Index: 968200 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 1.8251. Min Range: -1.8251

Max Act: 0.9207. Min Act: -0.0001

Data Index: 1308714 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 1.8251. Min Range: -1.8251

Max Act: 0.9667. Min Act: -0.0001

Data Index: 663983 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 1.8251. Min Range: -1.8251

Max Act: 0.9040. Min Act: -0.0001

Data Index: 244766 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 1.8251. Min Range: -1.8251

Max Act: 1.0209. Min Act: -0.0001

Data Index: 909234 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 1.8251. Min Range: -1.8251

Max Act: 0.8995. Min Act: -0.0001

Data Index: 194856 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 1.8251. Min Range: -1.8251

Max Act: 0.9116. Min Act: -0.0001

Data Index: 103434 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 1.8251. Min Range: -1.8251

Max Act: 0.9424. Min Act: -0.0001

Data Index: 303830 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 1.8251. Min Range: -1.8251

Max Act: 0.8277. Min Act: -0.0001

Data Index: 108788 (C4 (Web Text))

Max Activating Token Index: 70