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

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

Neuron 576 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: 0.0144. Min Range: -0.0144

Max Act: 0.0143. Min Act: -0.0007

Data Index: 208841 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0144. Min Act: -0.0006

Data Index: 459503 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0140. Min Act: -0.0006

Data Index: 61401 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0140. Min Act: -0.0006

Data Index: 521294 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0134. Min Act: -0.0006

Data Index: 687964 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0134. Min Act: -0.0006

Data Index: 134896 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0135. Min Act: -0.0006

Data Index: 849831 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0135. Min Act: -0.0006

Data Index: 20253 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0133. Min Act: -0.0006

Data Index: 361272 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0129. Min Act: -0.0006

Data Index: 501564 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0128. Min Act: -0.0006

Data Index: 959810 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1017241 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0130. Min Act: -0.0006

Data Index: 806519 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0127. Min Act: -0.0006

Data Index: 47317 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0126. Min Act: -0.0006

Data Index: 472221 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0125. Min Act: -0.0006

Data Index: 301304 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0125. Min Act: -0.0006

Data Index: 622814 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0123. Min Act: -0.0006

Data Index: 526929 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0123. Min Act: -0.0006

Data Index: 570131 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0122. Min Act: -0.0006

Data Index: 756049 (C4 (Web Text))

Max Activating Token Index: 810