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

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

Neuron 5108 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.7280. Min Act: -0.0000

Data Index: 2779 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5893. Min Act: -0.0000

Data Index: 273607 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6214. Min Act: -0.0001

Data Index: 1396300 (Python Code)

Max Activating Token Index: 709

Text #3

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6357. Min Act: -0.0000

Data Index: 549501 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6473. Min Act: -0.0000

Data Index: 547931 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6394. Min Act: -0.0000

Data Index: 182177 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6000. Min Act: -0.0000

Data Index: 788819 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5906. Min Act: -0.0000

Data Index: 688430 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1412247 (Python Code)

Max Activating Token Index: 330

Text #9

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5774. Min Act: -0.0000

Data Index: 479957 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1032937 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6233. Min Act: -0.0000

Data Index: 420319 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1202901 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1244720 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1169791 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1029853 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5446. Min Act: -0.0000

Data Index: 809684 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5517. Min Act: -0.0000

Data Index: 177568 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1254471 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1218026 (C4 (Web Text))

Max Activating Token Index: 235