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

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

Neuron 590 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.8508. Min Act: -0.0001

Data Index: 542352 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.8627. Min Act: -0.0001

Data Index: 236879 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.7483. Min Act: -0.0001

Data Index: 435620 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.7892. Min Act: -0.0001

Data Index: 14554 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.8081. Min Act: -0.0001

Data Index: 673358 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.8398. Min Act: -0.0001

Data Index: 539498 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.8065. Min Act: -0.0001

Data Index: 523108 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.8052. Min Act: -0.0001

Data Index: 514484 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.8023. Min Act: -0.0001

Data Index: 714222 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.7825. Min Act: -0.0001

Data Index: 344619 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.7886. Min Act: -0.0001

Data Index: 502484 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.7386. Min Act: -0.0001

Data Index: 1026146 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.7747. Min Act: -0.0001

Data Index: 1186124 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.7681. Min Act: -0.0001

Data Index: 601101 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.7383. Min Act: -0.0001

Data Index: 1240153 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.7638. Min Act: -0.0001

Data Index: 339483 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.7400. Min Act: -0.0001

Data Index: 1133571 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.7911. Min Act: -0.0001

Data Index: 211035 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.6996. Min Act: -0.0001

Data Index: 1171403 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.8627. Min Range: -0.8627

Max Act: 0.7101. Min Act: -0.0001

Data Index: 276908 (C4 (Web Text))

Max Activating Token Index: 70