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

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

Neuron 4647 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6793. Min Act: -0.0000

Data Index: 969345 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1019524 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5463. Min Act: -0.0000

Data Index: 472969 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5304. Min Act: -0.0000

Data Index: 57322 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1349763 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5200. Min Act: -0.0000

Data Index: 770319 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4974. Min Act: -0.0000

Data Index: 374878 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4954. Min Act: -0.0000

Data Index: 257669 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5084. Min Act: -0.0000

Data Index: 390496 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5080. Min Act: -0.0000

Data Index: 841388 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5110. Min Act: -0.0000

Data Index: 335936 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4596. Min Act: 0.0000

Data Index: 298339 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4581. Min Act: -0.0000

Data Index: 362863 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4683. Min Act: -0.0000

Data Index: 693370 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4779. Min Act: -0.0000

Data Index: 630517 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4769. Min Act: -0.0000

Data Index: 678430 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4799. Min Act: -0.0000

Data Index: 401396 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4571. Min Act: -0.0000

Data Index: 219111 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4670. Min Act: -0.0000

Data Index: 135384 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4288. Min Act: -0.0000

Data Index: 924250 (C4 (Web Text))

Max Activating Token Index: 869