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

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

Neuron 1851 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: 1.8267. Min Range: -1.8267

Max Act: 1.8205. Min Act: -0.0001

Data Index: 1106986 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.8267. Min Act: -0.0001

Data Index: 536189 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.8248. Min Act: -0.0001

Data Index: 1139197 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.7220. Min Act: -0.0001

Data Index: 170972 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.7573. Min Act: -0.0001

Data Index: 1338287 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.7025. Min Act: -0.0001

Data Index: 309537 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.6471. Min Act: -0.0001

Data Index: 484508 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.6941. Min Act: -0.0001

Data Index: 72371 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.7073. Min Act: -0.0001

Data Index: 651379 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.6303. Min Act: -0.0001

Data Index: 1222365 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.4946. Min Act: -0.0001

Data Index: 191007 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.4448. Min Act: -0.0001

Data Index: 863786 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.4082. Min Act: -0.0001

Data Index: 1064288 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.4288. Min Act: -0.0001

Data Index: 128024 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.3801. Min Act: -0.0001

Data Index: 336237 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.4131. Min Act: -0.0001

Data Index: 1343801 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.3585. Min Act: -0.0001

Data Index: 397387 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.3749. Min Act: -0.0001

Data Index: 1238611 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.2980. Min Act: -0.0001

Data Index: 940396 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.4175. Min Act: -0.0001

Data Index: 918693 (C4 (Web Text))

Max Activating Token Index: 617