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

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

Neuron 5735 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1875. Min Act: -0.0001

Data Index: 830191 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1699. Min Act: -0.0001

Data Index: 912803 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1565. Min Act: -0.0001

Data Index: 334108 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1562. Min Act: -0.0001

Data Index: 1291816 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1413. Min Act: -0.0001

Data Index: 83097 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1366. Min Act: -0.0001

Data Index: 1261755 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1439. Min Act: -0.0001

Data Index: 804553 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1345. Min Act: -0.0001

Data Index: 989447 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1396. Min Act: -0.0001

Data Index: 292548 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1578. Min Act: -0.0001

Data Index: 591924 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1505. Min Act: -0.0001

Data Index: 64428 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1251. Min Act: -0.0001

Data Index: 467369 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1628. Min Act: -0.0001

Data Index: 487904 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1062. Min Act: -0.0001

Data Index: 824874 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1259. Min Act: -0.0001

Data Index: 189631 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1127. Min Act: -0.0001

Data Index: 776314 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1629857 (Python Code)

Max Activating Token Index: 663

Text #17

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1077. Min Act: -0.0001

Data Index: 621891 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1481. Min Act: -0.0001

Data Index: 767500 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1375. Min Act: -0.0001

Data Index: 734476 (C4 (Web Text))

Max Activating Token Index: 344