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

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

Neuron 1474 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: 0.3605. Min Range: -0.3605

Max Act: 0.3605. Min Act: -0.0000

Data Index: 1423978 (Python Code)

Max Activating Token Index: 36

Text #1

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3473. Min Act: -0.0000

Data Index: 1609170 (Python Code)

Max Activating Token Index: 111

Text #2

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1469854 (Python Code)

Max Activating Token Index: 538

Text #3

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1386728 (Python Code)

Max Activating Token Index: 452

Text #4

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1649994 (Python Code)

Max Activating Token Index: 108

Text #5

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1640220 (Python Code)

Max Activating Token Index: 320

Text #6

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3328. Min Act: -0.0000

Data Index: 1459095 (Python Code)

Max Activating Token Index: 617

Text #7

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1526042 (Python Code)

Max Activating Token Index: 585

Text #8

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1510568 (Python Code)

Max Activating Token Index: 341

Text #9

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1467039 (Python Code)

Max Activating Token Index: 569

Text #10

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1470367 (Python Code)

Max Activating Token Index: 625

Text #11

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1583980 (Python Code)

Max Activating Token Index: 755

Text #12

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1545422 (Python Code)

Max Activating Token Index: 597

Text #13

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1445763 (Python Code)

Max Activating Token Index: 144

Text #14

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1606808 (Python Code)

Max Activating Token Index: 428

Text #15

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1465877 (Python Code)

Max Activating Token Index: 942

Text #16

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1562121 (Python Code)

Max Activating Token Index: 928

Text #17

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2634. Min Act: -0.0000

Data Index: 1409505 (Python Code)

Max Activating Token Index: 205

Text #18

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1537790 (Python Code)

Max Activating Token Index: 1022

Text #19

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1409739 (Python Code)

Max Activating Token Index: 97