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

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

Neuron 4401 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4619. Min Range: -1.4619

Max Act: 1.4619. Min Act: -0.0001

Data Index: 893092 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 1.4619. Min Range: -1.4619

Max Act: 1.1715. Min Act: -0.0001

Data Index: 730305 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 1.4619. Min Range: -1.4619

Max Act: 1.3099. Min Act: -0.0001

Data Index: 1093750 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 1.4619. Min Range: -1.4619

Max Act: 1.1311. Min Act: -0.0001

Data Index: 327031 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 1.4619. Min Range: -1.4619

Max Act: 1.1955. Min Act: -0.0001

Data Index: 227681 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 1.4619. Min Range: -1.4619

Max Act: 1.1553. Min Act: -0.0001

Data Index: 835546 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 1.4619. Min Range: -1.4619

Max Act: 1.2210. Min Act: -0.0001

Data Index: 104387 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 1.4619. Min Range: -1.4619

Max Act: 1.0635. Min Act: -0.0001

Data Index: 1351766 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 1.4619. Min Range: -1.4619

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1490111 (Python Code)

Max Activating Token Index: 374

Text #9

Max Range: 1.4619. Min Range: -1.4619

Max Act: 1.0944. Min Act: -0.0001

Data Index: 887611 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 1.4619. Min Range: -1.4619

Max Act: 1.0650. Min Act: -0.0001

Data Index: 640899 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 1.4619. Min Range: -1.4619

Max Act: 1.0311. Min Act: -0.0001

Data Index: 205218 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 1.4619. Min Range: -1.4619

Max Act: 1.0112. Min Act: -0.0001

Data Index: 480889 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.4619. Min Range: -1.4619

Max Act: 0.8934. Min Act: -0.0001

Data Index: 754968 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 1.4619. Min Range: -1.4619

Max Act: 0.8125. Min Act: -0.0001

Data Index: 761451 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 1.4619. Min Range: -1.4619

Max Act: 0.9401. Min Act: -0.0001

Data Index: 29871 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 1.4619. Min Range: -1.4619

Max Act: 0.9109. Min Act: -0.0001

Data Index: 755536 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 1.4619. Min Range: -1.4619

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1538347 (Python Code)

Max Activating Token Index: 391

Text #18

Max Range: 1.4619. Min Range: -1.4619

Max Act: 0.8120. Min Act: -0.0001

Data Index: 768393 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 1.4619. Min Range: -1.4619

Max Act: 0.8640. Min Act: -0.0001

Data Index: 226392 (C4 (Web Text))

Max Activating Token Index: 69