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

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

Neuron 3715 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: 0.3082. Min Range: -0.3082

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1050666 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2687. Min Act: -0.0000

Data Index: 446997 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2049. Min Act: -0.0000

Data Index: 332615 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.2311. Min Act: -0.0000

Data Index: 978747 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1831. Min Act: -0.0000

Data Index: 885075 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1748. Min Act: -0.0000

Data Index: 574942 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1749. Min Act: -0.0000

Data Index: 267427 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1225868 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1581. Min Act: -0.0000

Data Index: 620347 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1493. Min Act: -0.0000

Data Index: 1394011 (Python Code)

Max Activating Token Index: 436

Text #10

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1578. Min Act: -0.0000

Data Index: 290884 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1423. Min Act: -0.0000

Data Index: 345999 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1466. Min Act: -0.0000

Data Index: 595196 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1487. Min Act: -0.0000

Data Index: 441912 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1481. Min Act: -0.0000

Data Index: 98051 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1072242 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1455. Min Act: -0.0000

Data Index: 935990 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1377. Min Act: -0.0000

Data Index: 920246 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1401. Min Act: -0.0000

Data Index: 768735 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.3082. Min Range: -0.3082

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1264593 (C4 (Web Text))

Max Activating Token Index: 629