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

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

Neuron 1644 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: 0.2094. Min Range: -0.2094

Max Act: 0.2067. Min Act: -0.0000

Data Index: 291236 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.2094. Min Act: -0.0000

Data Index: 454716 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1730. Min Act: -0.0001

Data Index: 288233 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1777. Min Act: -0.0001

Data Index: 158866 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1321133 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1161995 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1614. Min Act: -0.0001

Data Index: 499443 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1674. Min Act: -0.0001

Data Index: 1091235 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1591. Min Act: -0.0000

Data Index: 775051 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1507. Min Act: -0.0000

Data Index: 200264 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1653. Min Act: -0.0000

Data Index: 317871 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1603. Min Act: -0.0001

Data Index: 259548 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1602. Min Act: -0.0001

Data Index: 710469 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1541. Min Act: -0.0001

Data Index: 479998 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1589. Min Act: -0.0001

Data Index: 11930 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1496. Min Act: -0.0001

Data Index: 528565 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1540. Min Act: -0.0000

Data Index: 533400 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1482. Min Act: -0.0001

Data Index: 974118 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1436. Min Act: -0.0001

Data Index: 1050731 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1530. Min Act: -0.0000

Data Index: 448795 (C4 (Web Text))

Max Activating Token Index: 194