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

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

Neuron 2355 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1827. Min Act: -0.0001

Data Index: 791262 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1940. Min Act: -0.0001

Data Index: 1045193 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1940. Min Act: -0.0001

Data Index: 1099706 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1875. Min Act: -0.0001

Data Index: 667133 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1830. Min Act: -0.0001

Data Index: 980915 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1877. Min Act: -0.0001

Data Index: 454268 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1943. Min Act: -0.0001

Data Index: 764525 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1751. Min Act: -0.0001

Data Index: 958737 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1949. Min Act: -0.0001

Data Index: 1117800 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1940. Min Act: -0.0001

Data Index: 290909 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1932. Min Act: -0.0001

Data Index: 772485 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1990. Min Act: -0.0001

Data Index: 349569 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1736. Min Act: -0.0000

Data Index: 616197 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1934. Min Act: -0.0001

Data Index: 1051780 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1806. Min Act: -0.0001

Data Index: 401188 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1778. Min Act: -0.0001

Data Index: 128790 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1841. Min Act: -0.0001

Data Index: 534211 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1960. Min Act: -0.0001

Data Index: 178493 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1832. Min Act: -0.0001

Data Index: 962065 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1883. Min Act: -0.0001

Data Index: 514027 (C4 (Web Text))

Max Activating Token Index: 424