Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2102 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1059795 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1295083 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1113920 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0153. Min Act: -0.0001

Data Index: 121421 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0135. Min Act: -0.0001

Data Index: 1196684 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0131. Min Act: -0.0001

Data Index: 680353 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0119. Min Act: -0.0001

Data Index: 927800 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0114. Min Act: -0.0001

Data Index: 161196 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0119. Min Act: -0.0001

Data Index: 79512 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0122. Min Act: -0.0001

Data Index: 990698 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0114. Min Act: -0.0002

Data Index: 700186 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0127. Min Act: -0.0002

Data Index: 679719 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0109. Min Act: -0.0001

Data Index: 648977 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0104. Min Act: -0.0002

Data Index: 538828 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0112. Min Act: -0.0001

Data Index: 1158079 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0113. Min Act: -0.0001

Data Index: 478206 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0107. Min Act: -0.0001

Data Index: 284672 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0115. Min Act: -0.0001

Data Index: 1282053 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0109. Min Act: -0.0001

Data Index: 328156 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0115. Min Act: -0.0001

Data Index: 602168 (C4 (Web Text))

Max Activating Token Index: 175