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

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

Neuron 3114 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0714. Min Act: -0.0000

Data Index: 746854 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0693. Min Act: -0.0000

Data Index: 787123 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0554. Min Act: -0.0000

Data Index: 1078138 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0582. Min Act: -0.0000

Data Index: 1641239 (Python Code)

Max Activating Token Index: 673

Text #4

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1375014 (Python Code)

Max Activating Token Index: 725

Text #5

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0554. Min Act: -0.0000

Data Index: 457757 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0566. Min Act: -0.0000

Data Index: 294319 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0574. Min Act: -0.0000

Data Index: 199213 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0533. Min Act: -0.0000

Data Index: 1544764 (Python Code)

Max Activating Token Index: 96

Text #9

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0529. Min Act: -0.0000

Data Index: 1473515 (Python Code)

Max Activating Token Index: 776

Text #10

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0427. Min Act: -0.0000

Data Index: 1637276 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1411234 (Python Code)

Max Activating Token Index: 730

Text #12

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1632991 (Python Code)

Max Activating Token Index: 912

Text #13

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0563. Min Act: -0.0000

Data Index: 1583329 (Python Code)

Max Activating Token Index: 405

Text #14

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0461. Min Act: -0.0000

Data Index: 1437191 (Python Code)

Max Activating Token Index: 575

Text #15

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0475. Min Act: -0.0000

Data Index: 1361379 (Python Code)

Max Activating Token Index: 607

Text #16

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0472. Min Act: -0.0000

Data Index: 564766 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0472. Min Act: -0.0000

Data Index: 865519 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1605034 (Python Code)

Max Activating Token Index: 715

Text #19

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0478. Min Act: -0.0000

Data Index: 513555 (C4 (Web Text))

Max Activating Token Index: 858