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

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

Neuron 4569 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.3587. Min Act: -0.0000

Data Index: 1313263 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.2115. Min Act: -0.0000

Data Index: 896964 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.2500. Min Act: -0.0000

Data Index: 295013 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1676. Min Act: -0.0000

Data Index: 344537 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1270. Min Act: -0.0000

Data Index: 399107 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1459. Min Act: -0.0000

Data Index: 853258 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1396. Min Act: -0.0000

Data Index: 314704 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1424. Min Act: -0.0000

Data Index: 1253420 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1456. Min Act: -0.0000

Data Index: 1591341 (Python Code)

Max Activating Token Index: 959

Text #9

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1146. Min Act: -0.0000

Data Index: 969763 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1003. Min Act: -0.0000

Data Index: 1108493 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.0710. Min Act: -0.0000

Data Index: 724392 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.0757. Min Act: -0.0000

Data Index: 329377 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.0218. Min Act: -0.0000

Data Index: 89395 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.0783. Min Act: -0.0000

Data Index: 106314 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.0407. Min Act: -0.0000

Data Index: 618662 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.0464. Min Act: -0.0000

Data Index: 880582 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.0137. Min Act: -0.0000

Data Index: 971339 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.0103. Min Act: -0.0000

Data Index: 1087965 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.0729. Min Act: -0.0000

Data Index: 553562 (C4 (Web Text))

Max Activating Token Index: 830