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

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

Neuron 818 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4960. Min Act: -0.0000

Data Index: 612804 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4583. Min Act: -0.0000

Data Index: 80437 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3558. Min Act: -0.0000

Data Index: 871269 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3586. Min Act: -0.0000

Data Index: 750717 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3639. Min Act: -0.0000

Data Index: 266931 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3168. Min Act: -0.0000

Data Index: 486476 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3180. Min Act: -0.0000

Data Index: 326965 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2939. Min Act: -0.0000

Data Index: 868324 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3309. Min Act: -0.0000

Data Index: 871218 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2890. Min Act: -0.0000

Data Index: 142206 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2940. Min Act: -0.0000

Data Index: 862067 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1122310 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3024. Min Act: -0.0000

Data Index: 10316 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2967. Min Act: -0.0000

Data Index: 249852 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2921. Min Act: -0.0000

Data Index: 490714 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1239270 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2815. Min Act: -0.0000

Data Index: 186898 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2755. Min Act: -0.0000

Data Index: 702349 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2832. Min Act: -0.0000

Data Index: 449899 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2904. Min Act: -0.0000

Data Index: 933164 (C4 (Web Text))

Max Activating Token Index: 820