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

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

Neuron 4887 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: 0.0383. Min Range: -0.0383

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1125108 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1301372 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0206. Min Act: -0.0003

Data Index: 102254 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0163. Min Act: -0.0003

Data Index: 986680 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0174. Min Act: -0.0003

Data Index: 474245 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0156. Min Act: -0.0003

Data Index: 5773 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0142. Min Act: -0.0003

Data Index: 1177357 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1153875 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0131. Min Act: -0.0003

Data Index: 282187 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1359143 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0132. Min Act: -0.0003

Data Index: 794617 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0131. Min Act: -0.0003

Data Index: 188678 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1205623 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0127. Min Act: -0.0003

Data Index: 1243497 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1296861 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0120. Min Act: -0.0003

Data Index: 7269 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1284854 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0114. Min Act: -0.0003

Data Index: 808481 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0118. Min Act: -0.0003

Data Index: 1278474 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0114. Min Act: -0.0003

Data Index: 683086 (C4 (Web Text))

Max Activating Token Index: 139