Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3722 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0824. Min Act: -0.0001

Data Index: 593933 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0698. Min Act: -0.0001

Data Index: 573440 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0128. Min Act: -0.0000

Data Index: 487268 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0125. Min Act: -0.0000

Data Index: 1325126 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0125. Min Act: -0.0000

Data Index: 949786 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0124. Min Act: -0.0000

Data Index: 1597765 (Python Code)

Max Activating Token Index: 69

Text #6

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0122. Min Act: -0.0001

Data Index: 1047181 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0122. Min Act: -0.0001

Data Index: 277803 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0116. Min Act: -0.0000

Data Index: 1177353 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0115. Min Act: -0.0000

Data Index: 6827 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0112. Min Act: -0.0000

Data Index: 414526 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0114. Min Act: -0.0000

Data Index: 203250 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0109. Min Act: -0.0000

Data Index: 903302 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0111. Min Act: -0.0000

Data Index: 760891 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0108. Min Act: -0.0000

Data Index: 1371675 (Python Code)

Max Activating Token Index: 135

Text #15

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0108. Min Act: -0.0000

Data Index: 1163567 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0108. Min Act: -0.0000

Data Index: 369635 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0107. Min Act: -0.0000

Data Index: 1479340 (Python Code)

Max Activating Token Index: 42

Text #18

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0111. Min Act: -0.0000

Data Index: 1399422 (Python Code)

Max Activating Token Index: 57

Text #19

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0110. Min Act: -0.0000

Data Index: 1457990 (Python Code)

Max Activating Token Index: 43