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

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

Neuron 865 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.1024. Min Act: -0.0001

Data Index: 586540 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0473. Min Act: -0.0001

Data Index: 1108123 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.9141. Min Act: -0.0002

Data Index: 667375 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0491. Min Act: -0.0002

Data Index: 910829 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0135. Min Act: -0.0001

Data Index: 852924 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0006. Min Act: -0.0002

Data Index: 94471 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.9886. Min Act: -0.0002

Data Index: 131200 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0099. Min Act: -0.0002

Data Index: 32138 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.9984. Min Act: -0.0002

Data Index: 1072073 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.9078. Min Act: -0.0001

Data Index: 329934 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.1079. Min Act: -0.0002

Data Index: 404532 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.9060. Min Act: -0.0002

Data Index: 271015 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.9109. Min Act: -0.0002

Data Index: 278093 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.9645. Min Act: -0.0001

Data Index: 560735 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.9054. Min Act: -0.0001

Data Index: 422725 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7765. Min Act: -0.0001

Data Index: 528852 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.8729. Min Act: -0.0002

Data Index: 185988 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7731. Min Act: -0.0001

Data Index: 379548 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.8283. Min Act: -0.0001

Data Index: 495373 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.8818. Min Act: -0.0002

Data Index: 1246881 (C4 (Web Text))

Max Activating Token Index: 567