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

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

Neuron 2170 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1795. Min Act: -0.0000

Data Index: 716551 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1708. Min Act: -0.0000

Data Index: 711691 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1020089 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1605. Min Act: -0.0000

Data Index: 912755 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1534. Min Act: -0.0000

Data Index: 21775 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1469. Min Act: -0.0000

Data Index: 898310 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1502. Min Act: -0.0000

Data Index: 877653 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1532. Min Act: -0.0000

Data Index: 500951 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1433. Min Act: -0.0000

Data Index: 316957 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1472. Min Act: -0.0000

Data Index: 906755 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1444. Min Act: -0.0000

Data Index: 220107 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1073988 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1089585 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1411. Min Act: -0.0000

Data Index: 600865 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1393. Min Act: -0.0000

Data Index: 367587 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1440. Min Act: -0.0000

Data Index: 667642 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1289946 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1372. Min Act: -0.0000

Data Index: 889785 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1320. Min Act: -0.0000

Data Index: 710005 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1344. Min Act: -0.0000

Data Index: 99385 (C4 (Web Text))

Max Activating Token Index: 962