Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3783 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1114. Min Range: -1.1114

Max Act: 1.1114. Min Act: -0.0001

Data Index: 1200517 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.9886. Min Act: -0.0001

Data Index: 835970 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 1.1114. Min Range: -1.1114

Max Act: 1.0718. Min Act: -0.0001

Data Index: 399416 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.9430. Min Act: -0.0001

Data Index: 1195668 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.9243. Min Act: -0.0001

Data Index: 1133432 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.9090. Min Act: -0.0001

Data Index: 342497 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.9006. Min Act: -0.0001

Data Index: 1296028 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.8703. Min Act: -0.0001

Data Index: 1076776 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.8426. Min Act: -0.0001

Data Index: 696669 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.8352. Min Act: -0.0001

Data Index: 110461 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.7724. Min Act: -0.0001

Data Index: 1291942 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.7886. Min Act: -0.0001

Data Index: 113629 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.7877. Min Act: -0.0001

Data Index: 1015310 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.7851. Min Act: -0.0001

Data Index: 464320 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.7858. Min Act: -0.0001

Data Index: 1129767 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.7156. Min Act: -0.0001

Data Index: 130075 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.7343. Min Act: -0.0001

Data Index: 964972 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.7115. Min Act: -0.0001

Data Index: 401606 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.7429. Min Act: -0.0001

Data Index: 531820 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 1.1114. Min Range: -1.1114

Max Act: 0.7361. Min Act: -0.0001

Data Index: 958917 (C4 (Web Text))

Max Activating Token Index: 106