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

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

Neuron 2688 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1162. Min Act: -0.0001

Data Index: 376780 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1189. Min Act: -0.0001

Data Index: 577678 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1052. Min Act: -0.0002

Data Index: 962652 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1020. Min Act: -0.0001

Data Index: 494835 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0930. Min Act: -0.0001

Data Index: 225389 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1076. Min Act: -0.0002

Data Index: 40368 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0935. Min Act: -0.0001

Data Index: 739721 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0953. Min Act: -0.0002

Data Index: 348831 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1057. Min Act: -0.0001

Data Index: 805258 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0941. Min Act: -0.0001

Data Index: 573905 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0933. Min Act: -0.0001

Data Index: 143142 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0930. Min Act: -0.0001

Data Index: 1032037 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1433739 (Python Code)

Max Activating Token Index: 909

Text #13

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0927. Min Act: -0.0002

Data Index: 406931 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1026. Min Act: -0.0001

Data Index: 1156802 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1539382 (Python Code)

Max Activating Token Index: 564

Text #16

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0898. Min Act: -0.0001

Data Index: 1486288 (Python Code)

Max Activating Token Index: 780

Text #17

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0872. Min Act: -0.0001

Data Index: 1433784 (Python Code)

Max Activating Token Index: 658

Text #18

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1570779 (Python Code)

Max Activating Token Index: 203

Text #19

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1407898 (Python Code)

Max Activating Token Index: 561