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

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

Neuron 1475 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: 0.7639. Min Range: -0.7639

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1411548 (Python Code)

Max Activating Token Index: 864

Text #1

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1459863 (Python Code)

Max Activating Token Index: 653

Text #2

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.6126. Min Act: 0.0000

Data Index: 1475746 (Python Code)

Max Activating Token Index: 281

Text #3

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1592172 (Python Code)

Max Activating Token Index: 648

Text #4

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1388419 (Python Code)

Max Activating Token Index: 172

Text #5

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1610495 (Python Code)

Max Activating Token Index: 646

Text #6

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1377027 (Python Code)

Max Activating Token Index: 311

Text #7

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1392741 (Python Code)

Max Activating Token Index: 266

Text #8

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1431157 (Python Code)

Max Activating Token Index: 307

Text #9

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1510906 (Python Code)

Max Activating Token Index: 905

Text #10

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1507364 (Python Code)

Max Activating Token Index: 776

Text #11

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1442107 (Python Code)

Max Activating Token Index: 930

Text #12

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.4558. Min Act: -0.0000

Data Index: 1555165 (Python Code)

Max Activating Token Index: 287

Text #13

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1655187 (Python Code)

Max Activating Token Index: 222

Text #14

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1638648 (Python Code)

Max Activating Token Index: 389

Text #15

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.4558. Min Act: -0.0000

Data Index: 1613507 (Python Code)

Max Activating Token Index: 306

Text #16

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1394405 (Python Code)

Max Activating Token Index: 121

Text #17

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.4796. Min Act: 0.0000

Data Index: 1520241 (Python Code)

Max Activating Token Index: 92

Text #18

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1396669 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1589073 (Python Code)

Max Activating Token Index: 690