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

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

Neuron 1465 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1571. Min Act: -0.0000

Data Index: 1081180 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1391. Min Act: -0.0001

Data Index: 843888 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1196. Min Act: -0.0001

Data Index: 274822 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1069888 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1126. Min Act: -0.0001

Data Index: 1197418 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0997. Min Act: -0.0001

Data Index: 391640 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0911. Min Act: -0.0000

Data Index: 644313 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0980. Min Act: -0.0001

Data Index: 174864 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0944. Min Act: -0.0000

Data Index: 422705 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0955. Min Act: -0.0001

Data Index: 900416 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0998. Min Act: -0.0001

Data Index: 817360 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0919. Min Act: -0.0001

Data Index: 451486 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0952. Min Act: -0.0001

Data Index: 567196 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0942. Min Act: -0.0001

Data Index: 522978 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0821. Min Act: -0.0001

Data Index: 48245 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0878. Min Act: -0.0001

Data Index: 707159 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0874. Min Act: -0.0001

Data Index: 90739 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0876. Min Act: -0.0001

Data Index: 464603 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0858. Min Act: -0.0001

Data Index: 212259 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0898. Min Act: -0.0001

Data Index: 431523 (C4 (Web Text))

Max Activating Token Index: 573