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

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

Neuron 1918 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: 0.0179. Min Range: -0.0179

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1161730 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0138. Min Act: -0.0003

Data Index: 1156470 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1114252 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1521432 (Python Code)

Max Activating Token Index: 822

Text #4

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0117. Min Act: -0.0002

Data Index: 818290 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0122. Min Act: -0.0003

Data Index: 435342 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0118. Min Act: -0.0003

Data Index: 985253 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0116. Min Act: -0.0003

Data Index: 1528762 (Python Code)

Max Activating Token Index: 259

Text #8

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1435960 (Python Code)

Max Activating Token Index: 235

Text #9

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0110. Min Act: -0.0003

Data Index: 489607 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0109. Min Act: -0.0003

Data Index: 59879 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0114. Min Act: -0.0003

Data Index: 37846 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0111. Min Act: -0.0003

Data Index: 1287879 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1323854 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1167672 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0110. Min Act: -0.0003

Data Index: 309747 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0109. Min Act: -0.0003

Data Index: 1270593 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0104. Min Act: -0.0003

Data Index: 396819 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1441981 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0106. Min Act: -0.0003

Data Index: 232229 (C4 (Web Text))

Max Activating Token Index: 130