Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1715 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.2506. Min Act: -0.0001

Data Index: 1188358 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.2303. Min Act: -0.0002

Data Index: 785208 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1989. Min Act: -0.0002

Data Index: 1008790 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1925. Min Act: -0.0002

Data Index: 361767 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.2131. Min Act: -0.0002

Data Index: 164956 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1923. Min Act: -0.0002

Data Index: 1284587 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1876. Min Act: -0.0002

Data Index: 39517 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1816. Min Act: -0.0002

Data Index: 997236 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1856. Min Act: -0.0001

Data Index: 754684 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1799. Min Act: -0.0002

Data Index: 1178563 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1785. Min Act: -0.0002

Data Index: 55351 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1793. Min Act: -0.0001

Data Index: 515746 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1834. Min Act: -0.0002

Data Index: 1134504 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1771. Min Act: -0.0002

Data Index: 728251 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1772. Min Act: -0.0001

Data Index: 1212432 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1814. Min Act: -0.0001

Data Index: 451123 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1860. Min Act: -0.0002

Data Index: 1235829 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1791. Min Act: -0.0002

Data Index: 790155 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1793. Min Act: -0.0002

Data Index: 1216365 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1715. Min Act: -0.0002

Data Index: 636412 (C4 (Web Text))

Max Activating Token Index: 964