Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 440 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0164. Min Act: -0.0005

Data Index: 608523 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1246036 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0128. Min Act: -0.0005

Data Index: 218440 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1288341 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0109. Min Act: -0.0006

Data Index: 912676 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0106. Min Act: -0.0006

Data Index: 201050 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0108. Min Act: -0.0006

Data Index: 13446 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0105. Min Act: -0.0006

Data Index: 158383 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0110. Min Act: -0.0006

Data Index: 221006 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1022920 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1168345 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0104. Min Act: -0.0005

Data Index: 1247700 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0102. Min Act: -0.0006

Data Index: 916082 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0101. Min Act: -0.0006

Data Index: 205580 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0103. Min Act: -0.0006

Data Index: 665484 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0102. Min Act: -0.0006

Data Index: 166457 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0099. Min Act: -0.0006

Data Index: 713121 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0097. Min Act: -0.0006

Data Index: 332520 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0101. Min Act: -0.0006

Data Index: 783625 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1176332 (C4 (Web Text))

Max Activating Token Index: 772