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

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

Neuron 116 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: 1.9873. Min Range: -1.9873

Max Act: 1.9843. Min Act: -0.0001

Data Index: 798047 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.9873. Min Act: -0.0001

Data Index: 1580717 (Python Code)

Max Activating Token Index: 167

Text #2

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.7021. Min Act: -0.0001

Data Index: 1602958 (Python Code)

Max Activating Token Index: 232

Text #3

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.6056. Min Act: -0.0001

Data Index: 1456194 (Python Code)

Max Activating Token Index: 294

Text #4

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.6292. Min Act: -0.0001

Data Index: 306638 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.2943. Min Act: -0.0001

Data Index: 1503418 (Python Code)

Max Activating Token Index: 951

Text #6

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.3332. Min Act: -0.0001

Data Index: 586784 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.3782. Min Act: -0.0001

Data Index: 1490889 (Python Code)

Max Activating Token Index: 426

Text #8

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.3132. Min Act: -0.0001

Data Index: 1597300 (Python Code)

Max Activating Token Index: 510

Text #9

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.2987. Min Act: -0.0001

Data Index: 1373562 (Python Code)

Max Activating Token Index: 380

Text #10

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.1392. Min Act: -0.0001

Data Index: 1268512 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.2619. Min Act: -0.0001

Data Index: 1067702 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.2984. Min Act: -0.0001

Data Index: 1069050 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.1986. Min Act: -0.0001

Data Index: 1333917 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.1425. Min Act: -0.0001

Data Index: 733035 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.1957. Min Act: -0.0001

Data Index: 1532652 (Python Code)

Max Activating Token Index: 780

Text #16

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.0766. Min Act: -0.0001

Data Index: 739522 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.1835. Min Act: -0.0001

Data Index: 349266 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.0265. Min Act: -0.0001

Data Index: 1308926 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 1.9873. Min Range: -1.9873

Max Act: 1.0510. Min Act: -0.0001

Data Index: 498673 (C4 (Web Text))

Max Activating Token Index: 140