Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1473 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1930. Min Act: -0.0002

Data Index: 97984 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1850. Min Act: -0.0002

Data Index: 245003 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1896. Min Act: -0.0002

Data Index: 676666 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1547. Min Act: -0.0002

Data Index: 303812 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1527. Min Act: -0.0002

Data Index: 791294 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1453. Min Act: -0.0002

Data Index: 1172386 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1384. Min Act: -0.0002

Data Index: 1344530 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1310. Min Act: -0.0001

Data Index: 687752 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1274. Min Act: -0.0002

Data Index: 577320 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1185. Min Act: -0.0002

Data Index: 40051 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1120. Min Act: -0.0002

Data Index: 453209 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1078. Min Act: -0.0002

Data Index: 1209334 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1309315 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1078. Min Act: -0.0002

Data Index: 901012 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1073. Min Act: -0.0002

Data Index: 399632 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1086. Min Act: -0.0002

Data Index: 972757 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1044. Min Act: -0.0002

Data Index: 985792 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1044. Min Act: -0.0002

Data Index: 550852 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1043. Min Act: -0.0002

Data Index: 866774 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1014. Min Act: -0.0002

Data Index: 45843 (C4 (Web Text))

Max Activating Token Index: 315