Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4908 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0133. Min Act: -0.0002

Data Index: 775118 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0125. Min Act: -0.0002

Data Index: 143358 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0124. Min Act: -0.0002

Data Index: 461581 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0122. Min Act: -0.0002

Data Index: 386255 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1422075 (Python Code)

Max Activating Token Index: 1008

Text #5

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1556317 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0119. Min Act: -0.0002

Data Index: 41354 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1069541 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0111. Min Act: -0.0002

Data Index: 664162 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1370444 (Python Code)

Max Activating Token Index: 1017

Text #10

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0111. Min Act: -0.0002

Data Index: 869107 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1502314 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1246559 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0111. Min Act: -0.0002

Data Index: 91394 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0110. Min Act: -0.0002

Data Index: 1289106 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0108. Min Act: -0.0002

Data Index: 149818 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0109. Min Act: -0.0002

Data Index: 402831 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0108. Min Act: -0.0002

Data Index: 254318 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0108. Min Act: -0.0002

Data Index: 76903 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0106. Min Act: -0.0002

Data Index: 681447 (C4 (Web Text))

Max Activating Token Index: 1017