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

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

Neuron 1636 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: 0.0199. Min Range: -0.0199

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1200724 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0186. Min Act: -0.0006

Data Index: 897050 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0186. Min Act: -0.0006

Data Index: 870186 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0191. Min Act: -0.0006

Data Index: 38715 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0175. Min Act: -0.0006

Data Index: 558976 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0164. Min Act: -0.0006

Data Index: 681586 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1017225 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1476264 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0141. Min Act: -0.0006

Data Index: 1450492 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1050013 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0141. Min Act: -0.0006

Data Index: 13670 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1580938 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0149. Min Act: -0.0006

Data Index: 627549 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1294269 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1023005 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0138. Min Act: -0.0006

Data Index: 185032 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0138. Min Act: -0.0006

Data Index: 160610 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1509540 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0156. Min Act: -0.0006

Data Index: 136631 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1393761 (Python Code)

Max Activating Token Index: 1023