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

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

Neuron 260 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2117. Min Range: -1.2117

Max Act: 1.2117. Min Act: -0.0000

Data Index: 221991 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 1.2117. Min Range: -1.2117

Max Act: 1.1883. Min Act: -0.0000

Data Index: 891888 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.8855. Min Act: 0.0000

Data Index: 1058639 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.8150. Min Act: -0.0000

Data Index: 603386 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.7079. Min Act: -0.0001

Data Index: 1199867 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.7715. Min Act: -0.0000

Data Index: 758750 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.7105. Min Act: -0.0000

Data Index: 242595 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.6108. Min Act: -0.0001

Data Index: 1237208 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.6914. Min Act: 0.0000

Data Index: 176371 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.5966. Min Act: -0.0001

Data Index: 697837 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.6539. Min Act: -0.0001

Data Index: 104502 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.6012. Min Act: -0.0001

Data Index: 837981 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.5527. Min Act: -0.0001

Data Index: 889998 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1143197 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.6086. Min Act: -0.0000

Data Index: 408191 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1240186 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.5977. Min Act: -0.0000

Data Index: 944163 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.4910. Min Act: -0.0000

Data Index: 649200 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.6124. Min Act: -0.0000

Data Index: 33820 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.5144. Min Act: -0.0000

Data Index: 117818 (C4 (Web Text))

Max Activating Token Index: 166