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

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

Neuron 5077 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: 0.1387. Min Range: -0.1387

Max Act: 0.1387. Min Act: -0.0002

Data Index: 28324 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1371. Min Act: -0.0003

Data Index: 1125933 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1304. Min Act: -0.0002

Data Index: 1265765 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1250. Min Act: -0.0002

Data Index: 274137 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1216. Min Act: -0.0002

Data Index: 1145238 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1224. Min Act: -0.0002

Data Index: 110713 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1122. Min Act: -0.0002

Data Index: 900148 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1140. Min Act: -0.0002

Data Index: 970372 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1136. Min Act: -0.0002

Data Index: 800806 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1159. Min Act: -0.0002

Data Index: 698604 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1121. Min Act: -0.0002

Data Index: 320976 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1131. Min Act: -0.0002

Data Index: 848780 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1116. Min Act: -0.0002

Data Index: 83193 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1118. Min Act: -0.0002

Data Index: 669737 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1104. Min Act: -0.0003

Data Index: 38403 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1096. Min Act: -0.0002

Data Index: 386973 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1091. Min Act: -0.0002

Data Index: 386373 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1079. Min Act: -0.0002

Data Index: 799314 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1079. Min Act: -0.0003

Data Index: 318128 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1087. Min Act: -0.0002

Data Index: 1163532 (C4 (Web Text))

Max Activating Token Index: 935