Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1757 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2911. Min Act: -0.0001

Data Index: 1547699 (Python Code)

Max Activating Token Index: 25

Text #1

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2786. Min Act: -0.0001

Data Index: 1550951 (Python Code)

Max Activating Token Index: 383

Text #2

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2746. Min Act: -0.0001

Data Index: 1445180 (Python Code)

Max Activating Token Index: 890

Text #3

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2731. Min Act: -0.0001

Data Index: 1428712 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2916. Min Act: -0.0001

Data Index: 1453686 (Python Code)

Max Activating Token Index: 679

Text #5

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2822. Min Act: -0.0001

Data Index: 1553746 (Python Code)

Max Activating Token Index: 844

Text #6

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2782. Min Act: -0.0001

Data Index: 1363001 (Python Code)

Max Activating Token Index: 926

Text #7

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2759. Min Act: -0.0001

Data Index: 1599019 (Python Code)

Max Activating Token Index: 777

Text #8

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2774. Min Act: -0.0001

Data Index: 1644905 (Python Code)

Max Activating Token Index: 550

Text #9

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2778. Min Act: -0.0001

Data Index: 1427334 (Python Code)

Max Activating Token Index: 859

Text #10

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2730. Min Act: -0.0001

Data Index: 1502228 (Python Code)

Max Activating Token Index: 924

Text #11

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2698. Min Act: -0.0001

Data Index: 1546212 (Python Code)

Max Activating Token Index: 907

Text #12

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2686. Min Act: -0.0001

Data Index: 1452893 (Python Code)

Max Activating Token Index: 639

Text #13

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2678. Min Act: -0.0001

Data Index: 1516018 (Python Code)

Max Activating Token Index: 437

Text #14

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2646. Min Act: -0.0001

Data Index: 1624576 (Python Code)

Max Activating Token Index: 399

Text #15

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2502. Min Act: -0.0001

Data Index: 1577087 (Python Code)

Max Activating Token Index: 770

Text #16

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2607. Min Act: -0.0001

Data Index: 1656865 (Python Code)

Max Activating Token Index: 793

Text #17

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2592. Min Act: -0.0001

Data Index: 1389884 (Python Code)

Max Activating Token Index: 440

Text #18

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2662. Min Act: -0.0001

Data Index: 1500364 (Python Code)

Max Activating Token Index: 126

Text #19

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2552. Min Act: -0.0001

Data Index: 1460670 (Python Code)

Max Activating Token Index: 476