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

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

Neuron 503 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0136. Min Act: -0.0004

Data Index: 175226 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0120. Min Act: -0.0004

Data Index: 245677 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0117. Min Act: -0.0004

Data Index: 1314847 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0116. Min Act: -0.0004

Data Index: 1603284 (Python Code)

Max Activating Token Index: 978

Text #4

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0115. Min Act: -0.0004

Data Index: 1335161 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0112. Min Act: -0.0003

Data Index: 1316310 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0114. Min Act: -0.0003

Data Index: 140917 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0112. Min Act: -0.0004

Data Index: 1118144 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0111. Min Act: -0.0004

Data Index: 953097 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0109. Min Act: -0.0004

Data Index: 1450302 (Python Code)

Max Activating Token Index: 842

Text #10

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0110. Min Act: -0.0004

Data Index: 497143 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0109. Min Act: -0.0003

Data Index: 1628034 (Python Code)

Max Activating Token Index: 530

Text #12

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0105. Min Act: -0.0004

Data Index: 582616 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1572366 (Python Code)

Max Activating Token Index: 450

Text #14

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1014773 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0102. Min Act: -0.0004

Data Index: 1388594 (Python Code)

Max Activating Token Index: 841

Text #16

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0103. Min Act: -0.0004

Data Index: 1339824 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0103. Min Act: -0.0004

Data Index: 998474 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0101. Min Act: -0.0004

Data Index: 38149 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0100. Min Act: -0.0003

Data Index: 1427137 (Python Code)

Max Activating Token Index: 670