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

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

Neuron 3921 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1423. Min Range: -2.1423

Max Act: 2.1423. Min Act: -0.0000

Data Index: 910431 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.7340. Min Act: -0.0000

Data Index: 902458 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.8139. Min Act: -0.0000

Data Index: 965865 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.7211. Min Act: -0.0000

Data Index: 1350834 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.5127. Min Act: -0.0000

Data Index: 954139 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.4408. Min Act: -0.0000

Data Index: 274507 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.4348. Min Act: -0.0000

Data Index: 116597 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.4360. Min Act: -0.0000

Data Index: 426488 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.5076. Min Act: -0.0000

Data Index: 912773 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.4035. Min Act: -0.0000

Data Index: 507257 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.4281. Min Act: -0.0000

Data Index: 1278715 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.3002. Min Act: -0.0000

Data Index: 931853 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.3615. Min Act: -0.0000

Data Index: 872881 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.2159. Min Act: -0.0000

Data Index: 81129 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.1127. Min Act: -0.0000

Data Index: 294851 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.1692. Min Act: -0.0000

Data Index: 118674 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.2262. Min Act: -0.0000

Data Index: 514271 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.3888. Min Act: -0.0000

Data Index: 1007532 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.2687. Min Act: -0.0000

Data Index: 1238604 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 2.1423. Min Range: -2.1423

Max Act: 1.1719. Min Act: -0.0000

Data Index: 223206 (C4 (Web Text))

Max Activating Token Index: 471