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

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

Neuron 2670 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: 0.1126. Min Range: -0.1126

Max Act: 0.1034. Min Act: -0.0001

Data Index: 869729 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1072. Min Act: -0.0001

Data Index: 773223 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1153603 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1005. Min Act: -0.0001

Data Index: 1221985 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1270871 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1126. Min Act: -0.0002

Data Index: 1137733 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1044572 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0901. Min Act: -0.0001

Data Index: 503580 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0974. Min Act: -0.0001

Data Index: 982008 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0961. Min Act: -0.0002

Data Index: 391375 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0925. Min Act: -0.0001

Data Index: 875966 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0884. Min Act: -0.0001

Data Index: 318394 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0968. Min Act: -0.0001

Data Index: 746725 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1019107 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0964. Min Act: -0.0001

Data Index: 727986 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0829. Min Act: -0.0001

Data Index: 206226 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0790. Min Act: -0.0001

Data Index: 58481 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0915. Min Act: -0.0002

Data Index: 480557 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0943. Min Act: -0.0002

Data Index: 505011 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1162814 (C4 (Web Text))

Max Activating Token Index: 942