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

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

Neuron 2251 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: 0.1080. Min Range: -0.1080

Max Act: 0.1068. Min Act: -0.0001

Data Index: 958115 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1080. Min Act: -0.0001

Data Index: 310241 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1010. Min Act: -0.0001

Data Index: 467609 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1037. Min Act: -0.0001

Data Index: 368925 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1172638 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0968. Min Act: -0.0001

Data Index: 387546 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1126364 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1263073 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0946. Min Act: -0.0001

Data Index: 902657 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0955. Min Act: -0.0001

Data Index: 632899 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0867. Min Act: -0.0001

Data Index: 176111 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0833. Min Act: -0.0001

Data Index: 170060 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0820. Min Act: -0.0001

Data Index: 372061 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1180804 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1086772 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0828. Min Act: -0.0001

Data Index: 1341944 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0832. Min Act: -0.0001

Data Index: 753221 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0734. Min Act: -0.0001

Data Index: 703374 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0757. Min Act: -0.0001

Data Index: 497401 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0723. Min Act: -0.0002

Data Index: 345666 (C4 (Web Text))

Max Activating Token Index: 848