Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4841 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0343. Min Act: -0.0001

Data Index: 423707 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0327. Min Act: -0.0001

Data Index: 841273 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1405693 (Python Code)

Max Activating Token Index: 360

Text #3

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0289. Min Act: -0.0001

Data Index: 222027 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0310. Min Act: -0.0001

Data Index: 511563 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1470086 (Python Code)

Max Activating Token Index: 327

Text #6

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1294320 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0247. Min Act: -0.0001

Data Index: 283739 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0232. Min Act: -0.0001

Data Index: 401860 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0206. Min Act: -0.0001

Data Index: 762603 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0245. Min Act: -0.0001

Data Index: 1336828 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0233. Min Act: -0.0001

Data Index: 569769 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0232. Min Act: -0.0001

Data Index: 923059 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0237. Min Act: -0.0001

Data Index: 301728 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0228. Min Act: -0.0001

Data Index: 215297 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0209. Min Act: -0.0001

Data Index: 5593 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0242. Min Act: -0.0001

Data Index: 249484 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0249. Min Act: -0.0001

Data Index: 1431568 (Python Code)

Max Activating Token Index: 279

Text #18

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0232. Min Act: -0.0001

Data Index: 35993 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0214. Min Act: -0.0001

Data Index: 1629054 (Python Code)

Max Activating Token Index: 364