Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4459 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0152. Min Act: -0.0002

Data Index: 689183 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0131. Min Act: -0.0002

Data Index: 244706 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0127. Min Act: -0.0002

Data Index: 702140 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0117. Min Act: -0.0003

Data Index: 71483 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1009741 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0121. Min Act: -0.0003

Data Index: 605669 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1533598 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1159428 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0111. Min Act: -0.0002

Data Index: 817194 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1485295 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0126. Min Act: -0.0002

Data Index: 301214 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0096. Min Act: -0.0002

Data Index: 700201 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0118. Min Act: -0.0002

Data Index: 1558815 (Python Code)

Max Activating Token Index: 102

Text #13

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1534905 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1428008 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0109. Min Act: -0.0003

Data Index: 1400343 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0098. Min Act: -0.0002

Data Index: 333423 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1074002 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0109. Min Act: -0.0003

Data Index: 697278 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.0152. Min Range: -0.0152

Max Act: 0.0108. Min Act: -0.0002

Data Index: 1239104 (C4 (Web Text))

Max Activating Token Index: 15