Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 502 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1553. Min Act: -0.0002

Data Index: 1485797 (Python Code)

Max Activating Token Index: 331

Text #1

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1190. Min Act: -0.0003

Data Index: 1560572 (Python Code)

Max Activating Token Index: 1013

Text #2

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0959. Min Act: -0.0002

Data Index: 1386032 (Python Code)

Max Activating Token Index: 620

Text #3

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0944. Min Act: -0.0003

Data Index: 1439542 (Python Code)

Max Activating Token Index: 487

Text #4

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1574084 (Python Code)

Max Activating Token Index: 993

Text #5

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0862. Min Act: -0.0003

Data Index: 1615456 (Python Code)

Max Activating Token Index: 621

Text #6

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0879. Min Act: -0.0002

Data Index: 1562639 (Python Code)

Max Activating Token Index: 280

Text #7

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1590758 (Python Code)

Max Activating Token Index: 366

Text #8

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0884. Min Act: -0.0003

Data Index: 1545367 (Python Code)

Max Activating Token Index: 922

Text #9

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0833. Min Act: -0.0003

Data Index: 1376576 (Python Code)

Max Activating Token Index: 253

Text #10

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1466981 (Python Code)

Max Activating Token Index: 370

Text #11

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1368752 (Python Code)

Max Activating Token Index: 881

Text #12

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1605378 (Python Code)

Max Activating Token Index: 708

Text #13

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1390486 (Python Code)

Max Activating Token Index: 986

Text #14

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1372798 (Python Code)

Max Activating Token Index: 182

Text #15

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1436915 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1407922 (Python Code)

Max Activating Token Index: 930

Text #17

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0821. Min Act: -0.0003

Data Index: 1431879 (Python Code)

Max Activating Token Index: 479

Text #18

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1431551 (Python Code)

Max Activating Token Index: 63

Text #19

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1373245 (Python Code)

Max Activating Token Index: 504