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

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

Neuron 1493 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: -0.0006

Data Index: 584602 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1077971 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0128. Min Act: -0.0006

Data Index: 229490 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0130. Min Act: -0.0005

Data Index: 849329 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0129. Min Act: -0.0006

Data Index: 995762 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0126. Min Act: -0.0006

Data Index: 484439 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0127. Min Act: -0.0006

Data Index: 352429 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0123. Min Act: -0.0006

Data Index: 592768 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0120. Min Act: -0.0006

Data Index: 606625 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0122. Min Act: -0.0006

Data Index: 191356 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0122. Min Act: -0.0006

Data Index: 350990 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0118. Min Act: -0.0006

Data Index: 118017 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0121. Min Act: -0.0006

Data Index: 819230 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0120. Min Act: -0.0006

Data Index: 945243 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0117. Min Act: -0.0006

Data Index: 731927 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0117. Min Act: -0.0006

Data Index: 225633 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1279041 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0117. Min Act: -0.0006

Data Index: 972951 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1106204 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0114. Min Act: -0.0006

Data Index: 255433 (C4 (Web Text))

Max Activating Token Index: 465