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

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

Neuron 1536 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: 0.1475. Min Range: -0.1475

Max Act: 0.1475. Min Act: -0.0000

Data Index: 370231 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1317. Min Act: -0.0000

Data Index: 942475 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1342. Min Act: -0.0000

Data Index: 956770 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1193. Min Act: -0.0000

Data Index: 525035 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1082. Min Act: -0.0000

Data Index: 530452 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1282601 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1088. Min Act: -0.0000

Data Index: 21851 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0943. Min Act: -0.0000

Data Index: 253533 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0975. Min Act: -0.0000

Data Index: 560529 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0981. Min Act: -0.0000

Data Index: 728685 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0942. Min Act: -0.0000

Data Index: 926814 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1020621 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0922. Min Act: -0.0000

Data Index: 214099 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0911. Min Act: -0.0000

Data Index: 93340 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1335698 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0882. Min Act: -0.0000

Data Index: 264310 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0811. Min Act: -0.0000

Data Index: 673296 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1011096 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0868. Min Act: -0.0000

Data Index: 674740 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0889. Min Act: -0.0000

Data Index: 182255 (C4 (Web Text))

Max Activating Token Index: 336