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

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

Neuron 702 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: 0.1064. Min Range: -0.1064

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1501282 (Python Code)

Max Activating Token Index: 661

Text #1

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1523433 (Python Code)

Max Activating Token Index: 775

Text #2

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1520490 (Python Code)

Max Activating Token Index: 505

Text #3

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1558867 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1648365 (Python Code)

Max Activating Token Index: 900

Text #5

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1571123 (Python Code)

Max Activating Token Index: 295

Text #6

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1425720 (Python Code)

Max Activating Token Index: 49

Text #7

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1601361 (Python Code)

Max Activating Token Index: 676

Text #8

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1490799 (Python Code)

Max Activating Token Index: 273

Text #9

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1400654 (Python Code)

Max Activating Token Index: 459

Text #10

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1621555 (Python Code)

Max Activating Token Index: 195

Text #11

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1601675 (Python Code)

Max Activating Token Index: 569

Text #12

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1494317 (Python Code)

Max Activating Token Index: 795

Text #13

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1513185 (Python Code)

Max Activating Token Index: 29

Text #14

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1370925 (Python Code)

Max Activating Token Index: 593

Text #15

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1385872 (Python Code)

Max Activating Token Index: 126

Text #16

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1566165 (Python Code)

Max Activating Token Index: 739

Text #17

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1425247 (Python Code)

Max Activating Token Index: 124

Text #18

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0908. Min Act: -0.0001

Data Index: 1548732 (Python Code)

Max Activating Token Index: 473

Text #19

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1466378 (Python Code)

Max Activating Token Index: 660