Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2509 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1938. Min Act: -0.0001

Data Index: 994869 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1088117 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1914. Min Act: -0.0000

Data Index: 909489 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1173507 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1674. Min Act: -0.0000

Data Index: 587882 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1664. Min Act: -0.0001

Data Index: 672244 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1591. Min Act: -0.0000

Data Index: 26221 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1474. Min Act: -0.0001

Data Index: 317573 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1579. Min Act: -0.0001

Data Index: 27544 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1560. Min Act: -0.0001

Data Index: 1413125 (Python Code)

Max Activating Token Index: 704

Text #10

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1557. Min Act: -0.0000

Data Index: 407090 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1545. Min Act: -0.0000

Data Index: 730948 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1424. Min Act: -0.0000

Data Index: 824927 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1458. Min Act: -0.0001

Data Index: 1217707 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1607139 (Python Code)

Max Activating Token Index: 351

Text #15

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1084149 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1447. Min Act: 0.0000

Data Index: 616400 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1430. Min Act: -0.0000

Data Index: 747075 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1433. Min Act: -0.0001

Data Index: 672048 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1379. Min Act: -0.0001

Data Index: 1622470 (Python Code)

Max Activating Token Index: 258