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

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

Neuron 6 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: 0.1203. Min Range: -0.1203

Max Act: 0.1203. Min Act: -0.0001

Data Index: 352199 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1030217 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1115. Min Act: -0.0001

Data Index: 30263 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1030. Min Act: -0.0001

Data Index: 917521 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0977. Min Act: -0.0001

Data Index: 24503 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0998. Min Act: -0.0001

Data Index: 1158479 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0989. Min Act: -0.0001

Data Index: 253415 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1016. Min Act: -0.0001

Data Index: 654606 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0987. Min Act: -0.0001

Data Index: 658630 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0944. Min Act: -0.0001

Data Index: 455088 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0973. Min Act: -0.0001

Data Index: 1104849 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1269949 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1341128 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0946. Min Act: -0.0001

Data Index: 719465 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1186615 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0867. Min Act: -0.0001

Data Index: 808676 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0929. Min Act: -0.0001

Data Index: 137641 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0939. Min Act: -0.0001

Data Index: 578442 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1349423 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0822. Min Act: -0.0001

Data Index: 489134 (C4 (Web Text))

Max Activating Token Index: 112