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

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

Neuron 5619 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: 0.7237. Min Range: -0.7237

Max Act: 0.7237. Min Act: -0.0000

Data Index: 277684 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6956. Min Act: -0.0000

Data Index: 90120 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6826. Min Act: -0.0000

Data Index: 723787 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1164592 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1379587 (Python Code)

Max Activating Token Index: 406

Text #5

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1545753 (Python Code)

Max Activating Token Index: 187

Text #6

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1119985 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.5456. Min Act: 0.0000

Data Index: 639032 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4996. Min Act: -0.0000

Data Index: 164201 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.5721. Min Act: -0.0000

Data Index: 54493 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4641. Min Act: -0.0000

Data Index: 895978 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1448774 (Python Code)

Max Activating Token Index: 498

Text #12

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4909. Min Act: -0.0000

Data Index: 128319 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1584330 (Python Code)

Max Activating Token Index: 280

Text #14

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.5705. Min Act: -0.0000

Data Index: 1398482 (Python Code)

Max Activating Token Index: 302

Text #15

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.5268. Min Act: -0.0000

Data Index: 58331 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1115920 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1426973 (Python Code)

Max Activating Token Index: 316

Text #18

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4371. Min Act: -0.0000

Data Index: 428450 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.5106. Min Act: -0.0000

Data Index: 21220 (C4 (Web Text))

Max Activating Token Index: 505