Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 910 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1185012 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0114. Min Act: -0.0006

Data Index: 915183 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1079339 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1288326 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0098. Min Act: -0.0006

Data Index: 357174 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0098. Min Act: -0.0006

Data Index: 726285 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0098. Min Act: -0.0006

Data Index: 161402 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0097. Min Act: -0.0006

Data Index: 838917 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1198917 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0095. Min Act: -0.0006

Data Index: 51110 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0095. Min Act: -0.0006

Data Index: 270054 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1274984 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1173199 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0090. Min Act: -0.0006

Data Index: 272873 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1215215 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0087. Min Act: -0.0006

Data Index: 1336293 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1195583 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0090. Min Act: -0.0006

Data Index: 586693 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0094. Min Act: -0.0006

Data Index: 129424 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0089. Min Act: -0.0006

Data Index: 144637 (C4 (Web Text))

Max Activating Token Index: 749