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

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

Neuron 3789 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: 2.1035. Min Range: -2.1035

Max Act: 2.1035. Min Act: -0.0000

Data Index: 554643 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.9050. Min Act: -0.0000

Data Index: 446349 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.9898. Min Act: -0.0000

Data Index: 1079588 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.9211. Min Act: -0.0000

Data Index: 505463 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.9203. Min Act: -0.0000

Data Index: 1340131 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.9040. Min Act: -0.0000

Data Index: 421026 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.9005. Min Act: -0.0000

Data Index: 1290602 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8297. Min Act: -0.0000

Data Index: 55029 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8592. Min Act: -0.0000

Data Index: 266482 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8571. Min Act: -0.0000

Data Index: 1256789 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8360. Min Act: -0.0000

Data Index: 879751 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8389. Min Act: -0.0000

Data Index: 1331564 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8330. Min Act: -0.0000

Data Index: 221366 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8389. Min Act: -0.0000

Data Index: 1171301 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.7396. Min Act: -0.0000

Data Index: 7042 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.9231. Min Act: -0.0000

Data Index: 317326 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8272. Min Act: -0.0000

Data Index: 976989 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8349. Min Act: -0.0000

Data Index: 1207265 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8134. Min Act: -0.0000

Data Index: 522928 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8732. Min Act: -0.0000

Data Index: 855564 (C4 (Web Text))

Max Activating Token Index: 359