Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2471 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4502. Min Act: -0.0000

Data Index: 999945 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4131. Min Act: -0.0000

Data Index: 613640 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4117. Min Act: -0.0000

Data Index: 403546 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3573. Min Act: 0.0000

Data Index: 983941 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3295. Min Act: -0.0000

Data Index: 901557 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3463. Min Act: 0.0000

Data Index: 851650 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3218. Min Act: 0.0000

Data Index: 234559 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3228. Min Act: -0.0000

Data Index: 436149 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3187. Min Act: -0.0000

Data Index: 709426 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3011. Min Act: -0.0000

Data Index: 341193 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1298354 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1287566 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1177885 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1124436 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3164. Min Act: 0.0000

Data Index: 549893 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.2889. Min Act: 0.0000

Data Index: 801005 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.2895. Min Act: -0.0000

Data Index: 350611 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.2536. Min Act: 0.0000

Data Index: 670356 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.2726. Min Act: -0.0000

Data Index: 619229 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.2882. Min Act: 0.0000

Data Index: 1324463 (C4 (Web Text))

Max Activating Token Index: 616