Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2437 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1762. Min Range: -1.1762

Max Act: 1.1720. Min Act: -0.0000

Data Index: 58041 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 1.1762. Min Range: -1.1762

Max Act: 1.1762. Min Act: -0.0000

Data Index: 625711 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 1.1762. Min Range: -1.1762

Max Act: 1.1599. Min Act: -0.0000

Data Index: 629169 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.9335. Min Act: -0.0000

Data Index: 173472 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 1.1762. Min Range: -1.1762

Max Act: 1.0491. Min Act: -0.0000

Data Index: 832476 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.9958. Min Act: -0.0000

Data Index: 797101 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.9691. Min Act: -0.0000

Data Index: 936826 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.9509. Min Act: -0.0000

Data Index: 885229 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.9838. Min Act: -0.0000

Data Index: 1353241 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1400038 (Python Code)

Max Activating Token Index: 777

Text #10

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.9446. Min Act: -0.0000

Data Index: 624396 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8662. Min Act: -0.0000

Data Index: 918317 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1107925 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8408. Min Act: -0.0000

Data Index: 113947 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1077682 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1516636 (Python Code)

Max Activating Token Index: 374

Text #16

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8331. Min Act: -0.0000

Data Index: 922132 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8315. Min Act: -0.0000

Data Index: 216858 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8086. Min Act: -0.0000

Data Index: 1586078 (Python Code)

Max Activating Token Index: 814

Text #19

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.7602. Min Act: -0.0000

Data Index: 603671 (C4 (Web Text))

Max Activating Token Index: 631