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

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

Neuron 5879 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1348109 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3979. Min Act: -0.0000

Data Index: 459109 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3772. Min Act: -0.0000

Data Index: 872131 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3827. Min Act: -0.0000

Data Index: 812265 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3693. Min Act: -0.0000

Data Index: 956774 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3783. Min Act: -0.0000

Data Index: 238992 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3602. Min Act: -0.0000

Data Index: 1353867 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3597. Min Act: -0.0000

Data Index: 337530 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3665. Min Act: -0.0000

Data Index: 129334 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3771. Min Act: -0.0000

Data Index: 618206 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3366. Min Act: -0.0000

Data Index: 954370 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3680. Min Act: -0.0000

Data Index: 703388 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3460. Min Act: -0.0000

Data Index: 818465 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3875. Min Act: -0.0000

Data Index: 459360 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1199680 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3439. Min Act: -0.0000

Data Index: 250216 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3367. Min Act: -0.0000

Data Index: 671010 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3204. Min Act: -0.0000

Data Index: 20769 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3318. Min Act: -0.0000

Data Index: 212785 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3218. Min Act: -0.0000

Data Index: 206220 (C4 (Web Text))

Max Activating Token Index: 897