Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1752 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1232. Min Act: -0.0002

Data Index: 1087579 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1085. Min Act: -0.0002

Data Index: 656330 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1180. Min Act: -0.0002

Data Index: 1091759 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1166. Min Act: -0.0002

Data Index: 748212 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1218082 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1051. Min Act: -0.0001

Data Index: 132793 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1080. Min Act: -0.0001

Data Index: 619079 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1087. Min Act: -0.0001

Data Index: 173630 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0961. Min Act: -0.0002

Data Index: 1126091 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1008636 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1161847 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1008. Min Act: -0.0002

Data Index: 516107 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1061. Min Act: -0.0001

Data Index: 596858 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1036. Min Act: -0.0002

Data Index: 713821 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1011. Min Act: -0.0001

Data Index: 370780 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1599725 (Python Code)

Max Activating Token Index: 465

Text #16

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0983. Min Act: -0.0002

Data Index: 20434 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1058084 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1428121 (Python Code)

Max Activating Token Index: 713

Text #19

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0974. Min Act: -0.0002

Data Index: 450843 (C4 (Web Text))

Max Activating Token Index: 55