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

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

Neuron 948 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.9091. Min Act: -0.0000

Data Index: 1113743 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.7222. Min Act: -0.0001

Data Index: 271156 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.7707. Min Act: -0.0001

Data Index: 952638 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.4084. Min Act: -0.0000

Data Index: 677960 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.1889. Min Act: -0.0000

Data Index: 914916 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.0978. Min Act: -0.0000

Data Index: 623197 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.1017. Min Act: -0.0000

Data Index: 1124348 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 2.9091. Min Range: -2.9091

Max Act: 1.8378. Min Act: -0.0000

Data Index: 96819 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 2.9091. Min Range: -2.9091

Max Act: 1.9909. Min Act: -0.0000

Data Index: 942789 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 2.9091. Min Range: -2.9091

Max Act: 1.8182. Min Act: -0.0000

Data Index: 1154184 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 2.9091. Min Range: -2.9091

Max Act: 1.8915. Min Act: -0.0000

Data Index: 158631 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 2.9091. Min Range: -2.9091

Max Act: 1.7121. Min Act: -0.0000

Data Index: 1277351 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 2.9091. Min Range: -2.9091

Max Act: 1.8990. Min Act: -0.0001

Data Index: 273647 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 2.9091. Min Range: -2.9091

Max Act: 1.8852. Min Act: -0.0001

Data Index: 151347 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 2.9091. Min Range: -2.9091

Max Act: 1.8719. Min Act: -0.0001

Data Index: 834151 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.0318. Min Act: -0.0001

Data Index: 971914 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 2.9091. Min Range: -2.9091

Max Act: 1.7678. Min Act: -0.0000

Data Index: 376269 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 2.9091. Min Range: -2.9091

Max Act: 1.7836. Min Act: -0.0000

Data Index: 1301598 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 2.9091. Min Range: -2.9091

Max Act: 1.7562. Min Act: -0.0000

Data Index: 16891 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 2.9091. Min Range: -2.9091

Max Act: 1.8787. Min Act: -0.0000

Data Index: 929148 (C4 (Web Text))

Max Activating Token Index: 344