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

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

Neuron 1036 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.3228. Min Act: -0.0001

Data Index: 438737 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.3168. Min Act: -0.0001

Data Index: 83363 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2940. Min Act: -0.0001

Data Index: 978419 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.3556. Min Act: -0.0000

Data Index: 83336 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2713. Min Act: -0.0001

Data Index: 450466 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2344. Min Act: -0.0001

Data Index: 1118116 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2652. Min Act: -0.0001

Data Index: 1320054 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2621. Min Act: -0.0001

Data Index: 1104409 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2544. Min Act: -0.0001

Data Index: 664947 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.3205. Min Act: -0.0000

Data Index: 736050 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2506. Min Act: -0.0001

Data Index: 489208 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2515. Min Act: -0.0001

Data Index: 1136079 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1672. Min Act: -0.0001

Data Index: 778284 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1979. Min Act: -0.0000

Data Index: 1027259 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1903. Min Act: -0.0001

Data Index: 166847 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1850. Min Act: -0.0001

Data Index: 706553 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2109. Min Act: -0.0001

Data Index: 434736 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1964. Min Act: -0.0001

Data Index: 1255826 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1736. Min Act: -0.0001

Data Index: 1318333 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1625. Min Act: -0.0001

Data Index: 455857 (C4 (Web Text))

Max Activating Token Index: 419