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

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

Neuron 311 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0003

Data Index: 1627072 (Python Code)

Max Activating Token Index: 668

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0114. Min Act: -0.0003

Data Index: 1507896 (Python Code)

Max Activating Token Index: 295

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1496382 (Python Code)

Max Activating Token Index: 908

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1613090 (Python Code)

Max Activating Token Index: 655

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1495346 (Python Code)

Max Activating Token Index: 936

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0104. Min Act: -0.0003

Data Index: 1469780 (Python Code)

Max Activating Token Index: 294

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1385935 (Python Code)

Max Activating Token Index: 676

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0100. Min Act: -0.0002

Data Index: 1480802 (Python Code)

Max Activating Token Index: 907

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0101. Min Act: -0.0003

Data Index: 1583296 (Python Code)

Max Activating Token Index: 642

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0100. Min Act: -0.0002

Data Index: 1455169 (Python Code)

Max Activating Token Index: 694

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0097. Min Act: -0.0003

Data Index: 302073 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1533253 (Python Code)

Max Activating Token Index: 872

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1506812 (Python Code)

Max Activating Token Index: 776

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1594949 (Python Code)

Max Activating Token Index: 479

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1513687 (Python Code)

Max Activating Token Index: 560

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0093. Min Act: -0.0003

Data Index: 1505282 (Python Code)

Max Activating Token Index: 123

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0093. Min Act: -0.0003

Data Index: 1639075 (Python Code)

Max Activating Token Index: 663

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0095. Min Act: -0.0003

Data Index: 1422463 (Python Code)

Max Activating Token Index: 865

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0093. Min Act: -0.0003

Data Index: 1625837 (Python Code)

Max Activating Token Index: 905

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1419224 (Python Code)

Max Activating Token Index: 871