Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3741 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.0857. Min Range: -6.0857

Max Act: 6.0857. Min Act: -0.0000

Data Index: 1123912 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 6.0857. Min Range: -6.0857

Max Act: 5.8901. Min Act: -0.0000

Data Index: 141930 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 6.0857. Min Range: -6.0857

Max Act: 5.4921. Min Act: -0.0000

Data Index: 632958 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 6.0857. Min Range: -6.0857

Max Act: 4.6085. Min Act: -0.0000

Data Index: 440830 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 6.0857. Min Range: -6.0857

Max Act: 4.6994. Min Act: -0.0000

Data Index: 188800 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 6.0857. Min Range: -6.0857

Max Act: 4.5108. Min Act: -0.0000

Data Index: 378523 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 6.0857. Min Range: -6.0857

Max Act: 4.8718. Min Act: -0.0000

Data Index: 668956 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 6.0857. Min Range: -6.0857

Max Act: 4.4715. Min Act: -0.0000

Data Index: 1103544 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 6.0857. Min Range: -6.0857

Max Act: 4.6437. Min Act: -0.0000

Data Index: 37392 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 6.0857. Min Range: -6.0857

Max Act: 4.4035. Min Act: -0.0000

Data Index: 187331 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 6.0857. Min Range: -6.0857

Max Act: 4.3969. Min Act: -0.0000

Data Index: 1324538 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 6.0857. Min Range: -6.0857

Max Act: 4.0908. Min Act: -0.0000

Data Index: 266880 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 6.0857. Min Range: -6.0857

Max Act: 4.0504. Min Act: -0.0000

Data Index: 312125 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 6.0857. Min Range: -6.0857

Max Act: 4.1992. Min Act: -0.0000

Data Index: 1139667 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 6.0857. Min Range: -6.0857

Max Act: 4.3618. Min Act: -0.0000

Data Index: 774356 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 6.0857. Min Range: -6.0857

Max Act: 4.1003. Min Act: -0.0000

Data Index: 448527 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 6.0857. Min Range: -6.0857

Max Act: 3.9009. Min Act: -0.0000

Data Index: 169458 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 6.0857. Min Range: -6.0857

Max Act: 4.0165. Min Act: -0.0000

Data Index: 361038 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 6.0857. Min Range: -6.0857

Max Act: 4.1477. Min Act: -0.0000

Data Index: 1146452 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 6.0857. Min Range: -6.0857

Max Act: 3.7600. Min Act: -0.0000

Data Index: 562424 (C4 (Web Text))

Max Activating Token Index: 315