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

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

Neuron 330 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: 0.2663. Min Range: -0.2663

Max Act: 0.2663. Min Act: -0.0001

Data Index: 140148 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.2481. Min Act: -0.0000

Data Index: 575734 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.2552. Min Act: -0.0001

Data Index: 1050698 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.2163. Min Act: -0.0000

Data Index: 286836 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.2022. Min Act: -0.0001

Data Index: 1288993 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1322159 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1967. Min Act: -0.0000

Data Index: 617786 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1910. Min Act: -0.0000

Data Index: 766834 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1756. Min Act: -0.0000

Data Index: 625567 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1730. Min Act: -0.0000

Data Index: 666617 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1758. Min Act: -0.0000

Data Index: 582822 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1617. Min Act: -0.0000

Data Index: 107843 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1674. Min Act: -0.0000

Data Index: 372745 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1671. Min Act: -0.0001

Data Index: 642201 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1527. Min Act: -0.0001

Data Index: 82786 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1650. Min Act: -0.0000

Data Index: 764559 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1645. Min Act: -0.0001

Data Index: 1249926 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1621. Min Act: -0.0000

Data Index: 112502 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1641. Min Act: -0.0001

Data Index: 449373 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1596. Min Act: -0.0000

Data Index: 403171 (C4 (Web Text))

Max Activating Token Index: 52