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

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

Neuron 236 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: 0.8891. Min Range: -0.8891

Max Act: 0.8891. Min Act: -0.0000

Data Index: 285070 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.7615. Min Act: -0.0000

Data Index: 35730 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.7808. Min Act: -0.0000

Data Index: 528641 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1485469 (Python Code)

Max Activating Token Index: 168

Text #4

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.7499. Min Act: -0.0000

Data Index: 35321 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.6798. Min Act: -0.0000

Data Index: 345946 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.6103. Min Act: -0.0000

Data Index: 335794 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5882. Min Act: -0.0000

Data Index: 239723 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5627. Min Act: -0.0000

Data Index: 25479 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5637. Min Act: -0.0000

Data Index: 702529 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1098540 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5103. Min Act: -0.0000

Data Index: 421817 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5081. Min Act: -0.0000

Data Index: 1465331 (Python Code)

Max Activating Token Index: 209

Text #13

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1228849 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.4507. Min Act: -0.0000

Data Index: 132402 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.4857. Min Act: -0.0000

Data Index: 1374828 (Python Code)

Max Activating Token Index: 27

Text #16

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.4904. Min Act: -0.0000

Data Index: 604850 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.4329. Min Act: -0.0000

Data Index: 1568122 (Python Code)

Max Activating Token Index: 37

Text #18

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.4412. Min Act: -0.0000

Data Index: 465712 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1400727 (Python Code)

Max Activating Token Index: 321