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

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

Neuron 4900 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1113. Min Act: -0.0002

Data Index: 810691 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1092. Min Act: -0.0002

Data Index: 139809 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1090. Min Act: -0.0002

Data Index: 1297259 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1021. Min Act: -0.0002

Data Index: 265035 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1007. Min Act: -0.0002

Data Index: 176793 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1029. Min Act: -0.0002

Data Index: 527890 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1041. Min Act: -0.0002

Data Index: 696900 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0996. Min Act: -0.0002

Data Index: 294079 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0927. Min Act: -0.0002

Data Index: 275121 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0988. Min Act: -0.0002

Data Index: 63789 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0957. Min Act: -0.0002

Data Index: 74077 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0982. Min Act: -0.0002

Data Index: 353795 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1220829 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0969. Min Act: -0.0002

Data Index: 343896 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0750. Min Act: -0.0002

Data Index: 99827 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0881. Min Act: -0.0002

Data Index: 259465 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1310075 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0925. Min Act: -0.0002

Data Index: 119082 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0908. Min Act: -0.0002

Data Index: 112224 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1059646 (C4 (Web Text))

Max Activating Token Index: 607