Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1835 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1381. Min Act: -0.0003

Data Index: 927239 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1017. Min Act: -0.0003

Data Index: 702561 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1206. Min Act: -0.0003

Data Index: 992828 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1260. Min Act: -0.0003

Data Index: 162326 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1106. Min Act: -0.0003

Data Index: 237592 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1132. Min Act: -0.0003

Data Index: 86476 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1089. Min Act: -0.0003

Data Index: 1321066 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1125. Min Act: -0.0003

Data Index: 327319 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1020. Min Act: -0.0003

Data Index: 873399 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1020. Min Act: -0.0003

Data Index: 1006513 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1048. Min Act: -0.0003

Data Index: 423622 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1048. Min Act: -0.0003

Data Index: 1194932 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0929. Min Act: -0.0003

Data Index: 953197 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0889. Min Act: -0.0003

Data Index: 491008 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1028. Min Act: -0.0003

Data Index: 1038518 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0884. Min Act: -0.0003

Data Index: 41170 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1028. Min Act: -0.0003

Data Index: 1170276 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1058. Min Act: -0.0003

Data Index: 921558 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0946. Min Act: -0.0003

Data Index: 1342255 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0982. Min Act: -0.0003

Data Index: 283419 (C4 (Web Text))

Max Activating Token Index: 57