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

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

Neuron 1246 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: 0.2083. Min Range: -0.2083

Max Act: 0.2083. Min Act: -0.0001

Data Index: 1302205 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.2051. Min Act: -0.0001

Data Index: 553030 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.2058. Min Act: -0.0001

Data Index: 801120 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.2008. Min Act: -0.0001

Data Index: 341192 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1952. Min Act: -0.0001

Data Index: 77201 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1873. Min Act: -0.0002

Data Index: 1230567 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1844. Min Act: -0.0002

Data Index: 1148524 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1792. Min Act: -0.0001

Data Index: 830116 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1930. Min Act: -0.0002

Data Index: 1110332 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1817. Min Act: -0.0002

Data Index: 543092 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1868. Min Act: -0.0002

Data Index: 627611 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1866. Min Act: -0.0002

Data Index: 783942 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1680. Min Act: -0.0002

Data Index: 688064 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1735. Min Act: -0.0002

Data Index: 96771 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1778. Min Act: -0.0002

Data Index: 124397 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1219873 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1802. Min Act: -0.0002

Data Index: 669885 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1717. Min Act: -0.0002

Data Index: 1277693 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1697. Min Act: -0.0002

Data Index: 747646 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1708. Min Act: -0.0002

Data Index: 958071 (C4 (Web Text))

Max Activating Token Index: 907