Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 262 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1584. Min Act: -0.0001

Data Index: 991043 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1013956 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1014939 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1362. Min Act: -0.0001

Data Index: 275042 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1227. Min Act: -0.0001

Data Index: 285948 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1126. Min Act: -0.0001

Data Index: 734722 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1154. Min Act: -0.0001

Data Index: 490708 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1072. Min Act: -0.0001

Data Index: 482698 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1079. Min Act: -0.0001

Data Index: 65445 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1281923 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1073819 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0945. Min Act: -0.0001

Data Index: 229963 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1028. Min Act: -0.0001

Data Index: 215888 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1030. Min Act: -0.0001

Data Index: 260039 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1039. Min Act: -0.0001

Data Index: 956393 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0994. Min Act: -0.0001

Data Index: 490913 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1148577 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1063316 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1028. Min Act: -0.0001

Data Index: 190817 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0920. Min Act: -0.0001

Data Index: 439382 (C4 (Web Text))

Max Activating Token Index: 119