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

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

Neuron 3499 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1756. Min Act: -0.0001

Data Index: 681969 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1753. Min Act: -0.0001

Data Index: 940200 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1724. Min Act: -0.0001

Data Index: 1351823 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1586. Min Act: -0.0001

Data Index: 107839 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1692. Min Act: -0.0001

Data Index: 305360 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1663. Min Act: -0.0001

Data Index: 141644 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1719. Min Act: -0.0001

Data Index: 96665 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1512. Min Act: -0.0001

Data Index: 340275 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1621. Min Act: -0.0001

Data Index: 476800 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1561. Min Act: -0.0001

Data Index: 811726 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1556. Min Act: -0.0001

Data Index: 515509 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1566. Min Act: -0.0001

Data Index: 881700 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1603. Min Act: -0.0001

Data Index: 793863 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1040487 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1531. Min Act: -0.0001

Data Index: 1013812 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1573. Min Act: -0.0001

Data Index: 248330 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1674. Min Act: -0.0001

Data Index: 516910 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1496. Min Act: -0.0001

Data Index: 650789 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1560. Min Act: -0.0001

Data Index: 32515 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1530. Min Act: -0.0001

Data Index: 889746 (C4 (Web Text))

Max Activating Token Index: 799