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

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

Neuron 1668 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1845. Min Act: -0.0001

Data Index: 367481 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1331. Min Act: -0.0001

Data Index: 775853 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1427. Min Act: -0.0001

Data Index: 214625 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1065. Min Act: -0.0001

Data Index: 591189 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1106. Min Act: -0.0001

Data Index: 827648 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1249351 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1084. Min Act: -0.0001

Data Index: 150815 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1109. Min Act: -0.0001

Data Index: 245241 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1230770 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1034. Min Act: -0.0001

Data Index: 318508 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1105. Min Act: -0.0001

Data Index: 457899 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1576601 (Python Code)

Max Activating Token Index: 365

Text #12

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1166. Min Act: -0.0001

Data Index: 613998 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1307554 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1530432 (Python Code)

Max Activating Token Index: 549

Text #15

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0947. Min Act: -0.0001

Data Index: 450059 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1494102 (Python Code)

Max Activating Token Index: 665

Text #17

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0892. Min Act: -0.0001

Data Index: 649212 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1023871 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.0824. Min Act: -0.0001

Data Index: 387622 (C4 (Web Text))

Max Activating Token Index: 716