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

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

Neuron 952 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: 0.1323. Min Range: -0.1323

Max Act: 0.1323. Min Act: -0.0006

Data Index: 990035 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1144. Min Act: -0.0006

Data Index: 387080 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1213. Min Act: -0.0006

Data Index: 1277994 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1200. Min Act: -0.0006

Data Index: 438412 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1188. Min Act: -0.0006

Data Index: 810006 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1062. Min Act: -0.0006

Data Index: 844778 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1050. Min Act: -0.0006

Data Index: 1106437 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1086. Min Act: -0.0006

Data Index: 563779 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1081. Min Act: -0.0006

Data Index: 186142 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1077. Min Act: -0.0006

Data Index: 185042 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1031. Min Act: -0.0006

Data Index: 1055752 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1072. Min Act: -0.0006

Data Index: 1232554 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1029. Min Act: -0.0006

Data Index: 255069 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1066. Min Act: -0.0006

Data Index: 242971 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1061. Min Act: -0.0006

Data Index: 939692 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1057. Min Act: -0.0006

Data Index: 1041842 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1099. Min Act: -0.0006

Data Index: 425191 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1008. Min Act: -0.0006

Data Index: 781863 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1047. Min Act: -0.0006

Data Index: 1042781 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1084. Min Act: -0.0006

Data Index: 740725 (C4 (Web Text))

Max Activating Token Index: 447