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

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

Neuron 2404 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.3485. Min Act: -0.0000

Data Index: 1218259 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1333568 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1067621 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2912. Min Act: -0.0000

Data Index: 669025 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1313575 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2685. Min Act: -0.0000

Data Index: 43484 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2682. Min Act: -0.0000

Data Index: 448522 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2681. Min Act: -0.0000

Data Index: 392283 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2570. Min Act: -0.0000

Data Index: 453787 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2717. Min Act: -0.0000

Data Index: 437146 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2648. Min Act: -0.0000

Data Index: 221233 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2696. Min Act: -0.0000

Data Index: 505162 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2619. Min Act: -0.0000

Data Index: 4518 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2609. Min Act: -0.0000

Data Index: 1297239 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2535. Min Act: -0.0000

Data Index: 741580 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2592. Min Act: -0.0000

Data Index: 725926 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1178623 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2586. Min Act: -0.0000

Data Index: 810059 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2594. Min Act: -0.0000

Data Index: 610108 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.3485. Min Range: -0.3485

Max Act: 0.2434. Min Act: -0.0000

Data Index: 770135 (C4 (Web Text))

Max Activating Token Index: 290