Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3971 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1242521 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2245. Min Act: -0.0000

Data Index: 926885 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2084. Min Act: -0.0000

Data Index: 474516 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2003. Min Act: -0.0000

Data Index: 682495 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1919. Min Act: -0.0000

Data Index: 554884 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1619090 (Python Code)

Max Activating Token Index: 428

Text #6

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1418104 (Python Code)

Max Activating Token Index: 718

Text #7

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1484399 (Python Code)

Max Activating Token Index: 924

Text #8

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1932. Min Act: -0.0000

Data Index: 646356 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1996. Min Act: -0.0000

Data Index: 121344 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1896. Min Act: -0.0000

Data Index: 810300 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1510181 (Python Code)

Max Activating Token Index: 117

Text #12

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1679. Min Act: -0.0000

Data Index: 237827 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1635. Min Act: -0.0000

Data Index: 138415 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1835. Min Act: -0.0000

Data Index: 916779 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1788. Min Act: -0.0000

Data Index: 126110 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1708. Min Act: -0.0000

Data Index: 63977 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1776. Min Act: -0.0000

Data Index: 595750 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1815. Min Act: -0.0000

Data Index: 249474 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1562. Min Act: -0.0000

Data Index: 749702 (C4 (Web Text))

Max Activating Token Index: 68