Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3000 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.2144. Min Act: -0.0001

Data Index: 737355 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1993. Min Act: -0.0001

Data Index: 618382 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1962. Min Act: -0.0001

Data Index: 511026 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1967. Min Act: -0.0001

Data Index: 488593 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.2012. Min Act: -0.0001

Data Index: 1176398 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1905. Min Act: -0.0001

Data Index: 819689 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1895. Min Act: -0.0001

Data Index: 983321 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1719. Min Act: -0.0001

Data Index: 1267036 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1669. Min Act: -0.0001

Data Index: 743624 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1609. Min Act: -0.0001

Data Index: 1196736 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1664. Min Act: -0.0001

Data Index: 395083 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1693. Min Act: -0.0001

Data Index: 210648 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1585. Min Act: -0.0001

Data Index: 606204 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1636. Min Act: -0.0001

Data Index: 695258 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1685. Min Act: -0.0001

Data Index: 142886 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1682. Min Act: -0.0001

Data Index: 907545 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1606. Min Act: -0.0001

Data Index: 740848 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1573. Min Act: -0.0001

Data Index: 501256 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1494. Min Act: -0.0001

Data Index: 649346 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1287311 (C4 (Web Text))

Max Activating Token Index: 571