Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1934 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0124. Min Act: -0.0006

Data Index: 513250 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0165. Min Act: -0.0006

Data Index: 1564237 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1403033 (Python Code)

Max Activating Token Index: 636

Text #3

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0136. Min Act: -0.0006

Data Index: 762613 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1514898 (Python Code)

Max Activating Token Index: 592

Text #5

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1457750 (Python Code)

Max Activating Token Index: 541

Text #6

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0116. Min Act: -0.0006

Data Index: 122371 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0128. Min Act: -0.0006

Data Index: 797796 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0115. Min Act: -0.0006

Data Index: 58146 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1169089 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1254241 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0119. Min Act: -0.0006

Data Index: 506573 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0129. Min Act: -0.0006

Data Index: 82189 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1230832 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0119. Min Act: -0.0006

Data Index: 641107 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0109. Min Act: -0.0006

Data Index: 837657 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0125. Min Act: -0.0006

Data Index: 505639 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1378518 (Python Code)

Max Activating Token Index: 251

Text #18

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0112. Min Act: -0.0006

Data Index: 987577 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1556081 (Python Code)

Max Activating Token Index: 459