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

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

Neuron 3771 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0755. Min Act: -0.0002

Data Index: 556263 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0656. Min Act: -0.0002

Data Index: 985140 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1417794 (Python Code)

Max Activating Token Index: 325

Text #3

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0588. Min Act: -0.0002

Data Index: 375170 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0572. Min Act: -0.0002

Data Index: 503574 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1313714 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1083798 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0548. Min Act: -0.0002

Data Index: 60726 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0499. Min Act: -0.0002

Data Index: 829267 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0527. Min Act: -0.0002

Data Index: 259597 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1260132 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0485. Min Act: -0.0002

Data Index: 263869 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1145808 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0477. Min Act: -0.0002

Data Index: 96858 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0491. Min Act: -0.0002

Data Index: 911595 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1124358 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0485. Min Act: -0.0002

Data Index: 119364 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0507. Min Act: -0.0002

Data Index: 246869 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1295736 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0459. Min Act: -0.0002

Data Index: 661848 (C4 (Web Text))

Max Activating Token Index: 900