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

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

Neuron 470 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: 0.0729. Min Range: -0.0729

Max Act: 0.0729. Min Act: -0.0000

Data Index: 41836 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0639. Min Act: -0.0000

Data Index: 976459 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0541. Min Act: -0.0000

Data Index: 726747 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1522649 (Python Code)

Max Activating Token Index: 532

Text #4

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0546. Min Act: -0.0000

Data Index: 866163 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0524. Min Act: -0.0000

Data Index: 1440080 (Python Code)

Max Activating Token Index: 908

Text #6

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1568068 (Python Code)

Max Activating Token Index: 350

Text #7

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0520. Min Act: -0.0000

Data Index: 340597 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0489. Min Act: -0.0000

Data Index: 1114606 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0495. Min Act: -0.0000

Data Index: 676027 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1574006 (Python Code)

Max Activating Token Index: 276

Text #11

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0517. Min Act: -0.0000

Data Index: 799546 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1657004 (Python Code)

Max Activating Token Index: 599

Text #13

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0474. Min Act: -0.0000

Data Index: 945218 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0481. Min Act: -0.0000

Data Index: 870086 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0464. Min Act: -0.0000

Data Index: 531874 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0460. Min Act: -0.0000

Data Index: 771229 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0510. Min Act: -0.0000

Data Index: 1413101 (Python Code)

Max Activating Token Index: 190

Text #18

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0492. Min Act: -0.0000

Data Index: 1440166 (Python Code)

Max Activating Token Index: 766

Text #19

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0462. Min Act: -0.0000

Data Index: 1530580 (Python Code)

Max Activating Token Index: 345