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

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

Neuron 2830 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: 0.5056. Min Range: -0.5056

Max Act: 0.5056. Min Act: -0.0001

Data Index: 1554536 (Python Code)

Max Activating Token Index: 248

Text #1

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.4760. Min Act: -0.0001

Data Index: 1587344 (Python Code)

Max Activating Token Index: 728

Text #2

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.4561. Min Act: -0.0001

Data Index: 45962 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.4311. Min Act: -0.0001

Data Index: 1414179 (Python Code)

Max Activating Token Index: 639

Text #4

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.4383. Min Act: -0.0001

Data Index: 997000 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.4184. Min Act: -0.0001

Data Index: 1516090 (Python Code)

Max Activating Token Index: 891

Text #6

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.4145. Min Act: -0.0001

Data Index: 1631726 (Python Code)

Max Activating Token Index: 339

Text #7

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.3905. Min Act: -0.0001

Data Index: 1639943 (Python Code)

Max Activating Token Index: 135

Text #8

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.4010. Min Act: -0.0001

Data Index: 1551564 (Python Code)

Max Activating Token Index: 843

Text #9

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.3974. Min Act: -0.0001

Data Index: 1546453 (Python Code)

Max Activating Token Index: 57

Text #10

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1305563 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.3900. Min Act: -0.0001

Data Index: 1607944 (Python Code)

Max Activating Token Index: 78

Text #12

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.3909. Min Act: -0.0000

Data Index: 913504 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.3966. Min Act: -0.0001

Data Index: 1650235 (Python Code)

Max Activating Token Index: 756

Text #14

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.3839. Min Act: -0.0001

Data Index: 1386191 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.3806. Min Act: -0.0001

Data Index: 1500834 (Python Code)

Max Activating Token Index: 939

Text #16

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.3816. Min Act: -0.0001

Data Index: 1498396 (Python Code)

Max Activating Token Index: 313

Text #17

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.3656. Min Act: -0.0001

Data Index: 1404260 (Python Code)

Max Activating Token Index: 940

Text #18

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.3775. Min Act: -0.0001

Data Index: 1447157 (Python Code)

Max Activating Token Index: 627

Text #19

Max Range: 0.5056. Min Range: -0.5056

Max Act: 0.3781. Min Act: -0.0001

Data Index: 1359888 (Python Code)

Max Activating Token Index: 966