Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 171 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.1091. Min Act: -0.0005

Data Index: 1251326 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0993. Min Act: -0.0005

Data Index: 963717 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0990. Min Act: -0.0005

Data Index: 324203 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0991. Min Act: -0.0005

Data Index: 640187 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0978. Min Act: -0.0005

Data Index: 1129541 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0980. Min Act: -0.0005

Data Index: 1262623 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0945. Min Act: -0.0005

Data Index: 197750 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0930. Min Act: -0.0005

Data Index: 378497 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0951. Min Act: -0.0005

Data Index: 910596 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0889. Min Act: -0.0005

Data Index: 1181161 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0938. Min Act: -0.0005

Data Index: 270108 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0850. Min Act: -0.0005

Data Index: 960549 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0967. Min Act: -0.0005

Data Index: 735698 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0880. Min Act: -0.0005

Data Index: 45165 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0873. Min Act: -0.0005

Data Index: 174203 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0851. Min Act: -0.0005

Data Index: 526741 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0886. Min Act: -0.0005

Data Index: 761642 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0865. Min Act: -0.0005

Data Index: 303059 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0946. Min Act: -0.0005

Data Index: 1097288 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0874. Min Act: -0.0005

Data Index: 556067 (C4 (Web Text))

Max Activating Token Index: 451