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

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

Neuron 3099 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0684. Min Act: -0.0002

Data Index: 488455 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0392. Min Act: -0.0003

Data Index: 381629 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0380. Min Act: -0.0003

Data Index: 21182 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0481. Min Act: -0.0003

Data Index: 130465 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0224. Min Act: -0.0002

Data Index: 436799 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9836. Min Act: -0.0002

Data Index: 777908 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9825. Min Act: -0.0002

Data Index: 905167 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9696. Min Act: -0.0002

Data Index: 1174293 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9701. Min Act: -0.0002

Data Index: 773581 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9699. Min Act: -0.0002

Data Index: 1328755 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9608. Min Act: -0.0002

Data Index: 312472 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9665. Min Act: -0.0002

Data Index: 695230 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9486. Min Act: -0.0002

Data Index: 102835 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9473. Min Act: -0.0002

Data Index: 703437 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9459. Min Act: -0.0003

Data Index: 1319083 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9307. Min Act: -0.0002

Data Index: 123271 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9433. Min Act: -0.0002

Data Index: 1084591 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9620. Min Act: -0.0002

Data Index: 935119 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9494. Min Act: -0.0002

Data Index: 404623 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9449. Min Act: -0.0002

Data Index: 933904 (C4 (Web Text))

Max Activating Token Index: 5