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

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

Neuron 5065 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2285. Min Act: -0.0000

Data Index: 449702 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1985. Min Act: -0.0000

Data Index: 449245 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1130511 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1910. Min Act: -0.0000

Data Index: 438179 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1964. Min Act: -0.0000

Data Index: 520202 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2043. Min Act: -0.0000

Data Index: 375839 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2007. Min Act: -0.0000

Data Index: 383046 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1961. Min Act: -0.0000

Data Index: 124435 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1747. Min Act: -0.0000

Data Index: 731573 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1719. Min Act: -0.0000

Data Index: 454652 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1822. Min Act: -0.0000

Data Index: 595154 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1287153 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1736. Min Act: -0.0000

Data Index: 818622 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1602. Min Act: 0.0000

Data Index: 116228 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1622. Min Act: -0.0000

Data Index: 325417 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1676. Min Act: -0.0000

Data Index: 359471 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1691. Min Act: -0.0000

Data Index: 603396 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1659. Min Act: -0.0000

Data Index: 380017 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1611. Min Act: -0.0000

Data Index: 434299 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1594. Min Act: -0.0000

Data Index: 894662 (C4 (Web Text))

Max Activating Token Index: 1003