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

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

Neuron 1691 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: 0.9339. Min Range: -0.9339

Max Act: 0.9339. Min Act: -0.0001

Data Index: 998194 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8647. Min Act: -0.0001

Data Index: 449248 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7641. Min Act: -0.0001

Data Index: 1292729 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7390. Min Act: -0.0001

Data Index: 544600 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8267. Min Act: -0.0001

Data Index: 368146 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7955. Min Act: -0.0001

Data Index: 160237 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7006. Min Act: -0.0001

Data Index: 159195 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7450. Min Act: -0.0001

Data Index: 687406 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7035. Min Act: -0.0001

Data Index: 362642 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7234. Min Act: -0.0001

Data Index: 105817 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6654. Min Act: -0.0001

Data Index: 161863 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6635. Min Act: -0.0001

Data Index: 1068735 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6031. Min Act: -0.0001

Data Index: 351924 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6525. Min Act: -0.0001

Data Index: 1214086 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6291. Min Act: -0.0001

Data Index: 573565 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6022. Min Act: -0.0001

Data Index: 306928 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6554. Min Act: -0.0001

Data Index: 247574 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.5803. Min Act: -0.0001

Data Index: 1054856 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.5863. Min Act: -0.0001

Data Index: 1101022 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.5466. Min Act: -0.0001

Data Index: 481370 (C4 (Web Text))

Max Activating Token Index: 90