Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4927 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.4570. Min Act: -0.0000

Data Index: 28075 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.4245. Min Act: -0.0000

Data Index: 954823 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1031662 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3800. Min Act: 0.0000

Data Index: 1084281 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3502. Min Act: -0.0000

Data Index: 105507 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3471. Min Act: -0.0000

Data Index: 888087 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.2958. Min Act: -0.0000

Data Index: 1276625 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3171. Min Act: -0.0000

Data Index: 834215 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1226508 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3126. Min Act: -0.0000

Data Index: 1133169 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.2921. Min Act: -0.0000

Data Index: 151062 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.3168. Min Act: -0.0000

Data Index: 82688 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.2941. Min Act: -0.0000

Data Index: 319192 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.2962. Min Act: -0.0000

Data Index: 913562 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.2892. Min Act: -0.0000

Data Index: 475109 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.2899. Min Act: -0.0000

Data Index: 200050 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.2697. Min Act: 0.0001

Data Index: 815121 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.2721. Min Act: -0.0000

Data Index: 313696 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.2769. Min Act: -0.0000

Data Index: 730837 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.4570. Min Range: -0.4570

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1060877 (C4 (Web Text))

Max Activating Token Index: 451