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

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

Neuron 2378 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0047. Min Act: -0.0002

Data Index: 976153 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0045. Min Act: -0.0003

Data Index: 1350168 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0045. Min Act: -0.0003

Data Index: 1163652 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0044. Min Act: -0.0003

Data Index: 950154 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0044. Min Act: -0.0003

Data Index: 19286 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0044. Min Act: -0.0003

Data Index: 826103 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0044. Min Act: -0.0003

Data Index: 329306 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0044. Min Act: -0.0003

Data Index: 1325496 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0044. Min Act: -0.0003

Data Index: 197799 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0044. Min Act: -0.0003

Data Index: 65191 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0043. Min Act: -0.0003

Data Index: 585009 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0043. Min Act: -0.0003

Data Index: 363069 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0043. Min Act: -0.0003

Data Index: 962534 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0042. Min Act: -0.0003

Data Index: 1035140 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0043. Min Act: -0.0002

Data Index: 127191 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0043. Min Act: -0.0003

Data Index: 1304024 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0043. Min Act: -0.0003

Data Index: 537311 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0043. Min Act: -0.0003

Data Index: 838158 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0042. Min Act: -0.0003

Data Index: 879958 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0043. Min Act: -0.0003

Data Index: 1003383 (C4 (Web Text))

Max Activating Token Index: 153