Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 297 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1440. Min Act: -0.0003

Data Index: 639487 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1237. Min Act: -0.0003

Data Index: 1123105 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1220. Min Act: -0.0003

Data Index: 117372 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1243. Min Act: -0.0003

Data Index: 1260732 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1186. Min Act: -0.0003

Data Index: 946718 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1179. Min Act: -0.0003

Data Index: 1197432 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1146. Min Act: -0.0003

Data Index: 592555 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1146. Min Act: -0.0003

Data Index: 1199141 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1157. Min Act: -0.0003

Data Index: 634846 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1133. Min Act: -0.0003

Data Index: 520827 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1126. Min Act: -0.0003

Data Index: 1141654 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1083. Min Act: -0.0003

Data Index: 1208851 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1117. Min Act: -0.0003

Data Index: 928068 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1116. Min Act: -0.0004

Data Index: 895065 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1044. Min Act: -0.0003

Data Index: 623232 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1106. Min Act: -0.0004

Data Index: 587411 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1150. Min Act: -0.0003

Data Index: 515214 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1069. Min Act: -0.0003

Data Index: 276122 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1081. Min Act: -0.0003

Data Index: 1127685 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1070. Min Act: -0.0003

Data Index: 1356289 (C4 (Web Text))

Max Activating Token Index: 692