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

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

Neuron 2531 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4858. Min Range: -2.4858

Max Act: 2.4858. Min Act: -0.0000

Data Index: 883437 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 2.4858. Min Range: -2.4858

Max Act: 2.2749. Min Act: -0.0000

Data Index: 1189760 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 2.4858. Min Range: -2.4858

Max Act: 2.3914. Min Act: -0.0000

Data Index: 870391 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 2.4858. Min Range: -2.4858

Max Act: 2.2323. Min Act: -0.0000

Data Index: 1025455 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 2.4858. Min Range: -2.4858

Max Act: 1.9113. Min Act: -0.0000

Data Index: 149555 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 2.4858. Min Range: -2.4858

Max Act: 2.2020. Min Act: -0.0000

Data Index: 594182 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 2.4858. Min Range: -2.4858

Max Act: 2.1523. Min Act: -0.0000

Data Index: 242006 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 2.4858. Min Range: -2.4858

Max Act: 1.9754. Min Act: -0.0000

Data Index: 1223950 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 2.4858. Min Range: -2.4858

Max Act: 1.9973. Min Act: -0.0000

Data Index: 528493 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 2.4858. Min Range: -2.4858

Max Act: 1.9627. Min Act: -0.0000

Data Index: 973164 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 2.4858. Min Range: -2.4858

Max Act: 1.9518. Min Act: -0.0000

Data Index: 559145 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 2.4858. Min Range: -2.4858

Max Act: 1.9064. Min Act: -0.0000

Data Index: 855934 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 2.4858. Min Range: -2.4858

Max Act: 2.0409. Min Act: -0.0000

Data Index: 113241 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 2.4858. Min Range: -2.4858

Max Act: 1.9538. Min Act: -0.0000

Data Index: 1059866 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 2.4858. Min Range: -2.4858

Max Act: 1.7823. Min Act: -0.0000

Data Index: 787100 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 2.4858. Min Range: -2.4858

Max Act: 1.8505. Min Act: -0.0000

Data Index: 792505 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 2.4858. Min Range: -2.4858

Max Act: 1.8451. Min Act: -0.0000

Data Index: 1576623 (Python Code)

Max Activating Token Index: 950

Text #17

Max Range: 2.4858. Min Range: -2.4858

Max Act: 1.7403. Min Act: -0.0000

Data Index: 940763 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 2.4858. Min Range: -2.4858

Max Act: 1.7000. Min Act: -0.0000

Data Index: 1430499 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 2.4858. Min Range: -2.4858

Max Act: 1.7384. Min Act: -0.0000

Data Index: 907289 (C4 (Web Text))

Max Activating Token Index: 285