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

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

Neuron 916 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: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0004

Data Index: 970105 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0004

Data Index: 1206145 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0124. Min Act: -0.0004

Data Index: 435435 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0124. Min Act: -0.0004

Data Index: 818231 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0123. Min Act: -0.0004

Data Index: 324499 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0121. Min Act: -0.0004

Data Index: 1047818 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0119. Min Act: -0.0004

Data Index: 656186 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0120. Min Act: -0.0004

Data Index: 503647 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0119. Min Act: -0.0004

Data Index: 31073 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0118. Min Act: -0.0004

Data Index: 11681 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0119. Min Act: -0.0004

Data Index: 1036787 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0004

Data Index: 1272702 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0004

Data Index: 576538 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0004

Data Index: 821572 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0004

Data Index: 1098778 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0004

Data Index: 165183 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0004

Data Index: 967905 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0004

Data Index: 1335296 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0004

Data Index: 83419 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0004

Data Index: 254809 (C4 (Web Text))

Max Activating Token Index: 665