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

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

Neuron 1454 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0391. Min Act: -0.0001

Data Index: 1327836 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0204. Min Act: -0.0001

Data Index: 797651 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0177. Min Act: -0.0001

Data Index: 994400 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0188. Min Act: -0.0001

Data Index: 830829 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0154. Min Act: -0.0001

Data Index: 945241 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0156. Min Act: -0.0001

Data Index: 314268 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0161. Min Act: -0.0001

Data Index: 1025049 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0145. Min Act: -0.0002

Data Index: 516920 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0119. Min Act: -0.0001

Data Index: 326624 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0145. Min Act: -0.0001

Data Index: 615480 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0143. Min Act: -0.0001

Data Index: 1218708 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0149. Min Act: -0.0001

Data Index: 1274505 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0131. Min Act: -0.0001

Data Index: 370734 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0132. Min Act: -0.0001

Data Index: 1306033 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0142. Min Act: -0.0002

Data Index: 193851 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0130. Min Act: -0.0001

Data Index: 563383 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0133. Min Act: -0.0002

Data Index: 970555 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0123. Min Act: -0.0001

Data Index: 237588 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0131. Min Act: -0.0001

Data Index: 351368 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0136. Min Act: -0.0001

Data Index: 140908 (C4 (Web Text))

Max Activating Token Index: 1006