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

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

Neuron 1508 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7738. Min Act: -0.0001

Data Index: 1528660 (Python Code)

Max Activating Token Index: 1016

Text #1

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7599. Min Act: -0.0001

Data Index: 1384470 (Python Code)

Max Activating Token Index: 947

Text #2

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7603. Min Act: -0.0001

Data Index: 1378348 (Python Code)

Max Activating Token Index: 926

Text #3

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7813. Min Act: -0.0001

Data Index: 1441110 (Python Code)

Max Activating Token Index: 1001

Text #4

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7555. Min Act: -0.0001

Data Index: 1532879 (Python Code)

Max Activating Token Index: 1000

Text #5

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7402. Min Act: -0.0001

Data Index: 1623385 (Python Code)

Max Activating Token Index: 1013

Text #6

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7029. Min Act: -0.0001

Data Index: 1455785 (Python Code)

Max Activating Token Index: 1005

Text #7

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7210. Min Act: -0.0001

Data Index: 1451015 (Python Code)

Max Activating Token Index: 984

Text #8

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.6709. Min Act: -0.0001

Data Index: 1587645 (Python Code)

Max Activating Token Index: 890

Text #9

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7175. Min Act: -0.0001

Data Index: 1649855 (Python Code)

Max Activating Token Index: 998

Text #10

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7153. Min Act: -0.0001

Data Index: 1603115 (Python Code)

Max Activating Token Index: 968

Text #11

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7178. Min Act: -0.0001

Data Index: 1422607 (Python Code)

Max Activating Token Index: 959

Text #12

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7627. Min Act: -0.0001

Data Index: 1415707 (Python Code)

Max Activating Token Index: 969

Text #13

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7110. Min Act: -0.0001

Data Index: 1472831 (Python Code)

Max Activating Token Index: 1002

Text #14

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7348. Min Act: -0.0001

Data Index: 1578287 (Python Code)

Max Activating Token Index: 995

Text #15

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7581. Min Act: -0.0001

Data Index: 1413892 (Python Code)

Max Activating Token Index: 986

Text #16

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7567. Min Act: -0.0001

Data Index: 1425012 (Python Code)

Max Activating Token Index: 986

Text #17

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7313. Min Act: -0.0001

Data Index: 1450373 (Python Code)

Max Activating Token Index: 1017

Text #18

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7282. Min Act: -0.0001

Data Index: 1544863 (Python Code)

Max Activating Token Index: 1011

Text #19

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.6989. Min Act: -0.0001

Data Index: 1458256 (Python Code)

Max Activating Token Index: 908