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

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

Neuron 1066 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0111. Min Act: -0.0006

Data Index: 545935 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0107. Min Act: -0.0005

Data Index: 1638932 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0108. Min Act: -0.0006

Data Index: 943612 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1277204 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1274619 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0105. Min Act: -0.0006

Data Index: 40866 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0103. Min Act: -0.0006

Data Index: 190966 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1352281 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0103. Min Act: -0.0006

Data Index: 851712 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0102. Min Act: -0.0007

Data Index: 803445 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0104. Min Act: -0.0006

Data Index: 22157 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0102. Min Act: -0.0006

Data Index: 888961 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0102. Min Act: -0.0005

Data Index: 1406262 (Python Code)

Max Activating Token Index: 685

Text #13

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0104. Min Act: -0.0006

Data Index: 89588 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1252223 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0103. Min Act: -0.0006

Data Index: 79604 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0102. Min Act: -0.0007

Data Index: 585961 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1296970 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1444353 (Python Code)

Max Activating Token Index: 759

Text #19

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1555708 (Python Code)

Max Activating Token Index: 609