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

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

Neuron 357 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: 0.1605. Min Range: -0.1605

Max Act: 0.1605. Min Act: -0.0002

Data Index: 627214 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1327. Min Act: -0.0002

Data Index: 292461 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1417. Min Act: -0.0002

Data Index: 407625 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1300. Min Act: -0.0002

Data Index: 831149 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1289. Min Act: -0.0002

Data Index: 939579 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1238. Min Act: -0.0002

Data Index: 506249 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1248. Min Act: -0.0002

Data Index: 878355 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1225. Min Act: -0.0002

Data Index: 258882 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1233. Min Act: -0.0002

Data Index: 1217911 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1190. Min Act: -0.0002

Data Index: 64214 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1156. Min Act: -0.0002

Data Index: 450125 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1144. Min Act: -0.0002

Data Index: 372388 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1114. Min Act: -0.0002

Data Index: 1242800 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1087. Min Act: -0.0002

Data Index: 567186 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1074. Min Act: -0.0002

Data Index: 908575 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1038. Min Act: -0.0002

Data Index: 1000558 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1100. Min Act: -0.0002

Data Index: 363763 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1051. Min Act: -0.0002

Data Index: 950225 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1111. Min Act: -0.0002

Data Index: 958830 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1069. Min Act: -0.0002

Data Index: 980901 (C4 (Web Text))

Max Activating Token Index: 842