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

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

Neuron 3669 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.3761. Min Act: -0.0000

Data Index: 658727 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2621. Min Act: -0.0000

Data Index: 155979 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.1529. Min Act: -0.0000

Data Index: 1136468 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2541. Min Act: -0.0000

Data Index: 662738 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.1360. Min Act: -0.0000

Data Index: 278836 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 2.3761. Min Range: -2.3761

Max Act: 1.9859. Min Act: -0.0000

Data Index: 1599598 (Python Code)

Max Activating Token Index: 799

Text #6

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.0447. Min Act: -0.0000

Data Index: 1365194 (Python Code)

Max Activating Token Index: 87

Text #7

Max Range: 2.3761. Min Range: -2.3761

Max Act: 1.9197. Min Act: -0.0000

Data Index: 1535425 (Python Code)

Max Activating Token Index: 828

Text #8

Max Range: 2.3761. Min Range: -2.3761

Max Act: 1.9824. Min Act: -0.0000

Data Index: 866365 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 2.3761. Min Range: -2.3761

Max Act: 1.9404. Min Act: -0.0000

Data Index: 1558813 (Python Code)

Max Activating Token Index: 332

Text #10

Max Range: 2.3761. Min Range: -2.3761

Max Act: 1.9324. Min Act: -0.0000

Data Index: 1586013 (Python Code)

Max Activating Token Index: 549

Text #11

Max Range: 2.3761. Min Range: -2.3761

Max Act: 1.9301. Min Act: -0.0000

Data Index: 13968 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 2.3761. Min Range: -2.3761

Max Act: 1.8125. Min Act: -0.0000

Data Index: 825093 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 2.3761. Min Range: -2.3761

Max Act: 1.8781. Min Act: -0.0000

Data Index: 1405474 (Python Code)

Max Activating Token Index: 238

Text #14

Max Range: 2.3761. Min Range: -2.3761

Max Act: 1.7610. Min Act: -0.0000

Data Index: 1530458 (Python Code)

Max Activating Token Index: 958

Text #15

Max Range: 2.3761. Min Range: -2.3761

Max Act: 1.8725. Min Act: -0.0000

Data Index: 1596075 (Python Code)

Max Activating Token Index: 321

Text #16

Max Range: 2.3761. Min Range: -2.3761

Max Act: 1.7554. Min Act: -0.0000

Data Index: 1564270 (Python Code)

Max Activating Token Index: 855

Text #17

Max Range: 2.3761. Min Range: -2.3761

Max Act: 1.8480. Min Act: -0.0000

Data Index: 924524 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 2.3761. Min Range: -2.3761

Max Act: 1.8571. Min Act: -0.0000

Data Index: 1213066 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 2.3761. Min Range: -2.3761

Max Act: 1.9344. Min Act: -0.0000

Data Index: 1384359 (Python Code)

Max Activating Token Index: 326