Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1695 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4534. Min Act: -0.0001

Data Index: 1151790 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3571. Min Act: -0.0001

Data Index: 1296577 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3818. Min Act: -0.0001

Data Index: 550805 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4251. Min Act: -0.0001

Data Index: 1050941 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4021. Min Act: -0.0001

Data Index: 543400 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3854. Min Act: -0.0001

Data Index: 808921 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3246. Min Act: -0.0001

Data Index: 425747 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4229. Min Act: -0.0001

Data Index: 1019283 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4127. Min Act: -0.0001

Data Index: 349306 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3797. Min Act: -0.0001

Data Index: 1086275 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3978. Min Act: -0.0001

Data Index: 682309 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3815. Min Act: -0.0001

Data Index: 784894 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3944. Min Act: -0.0001

Data Index: 1108230 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3964. Min Act: -0.0001

Data Index: 606870 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4070. Min Act: -0.0001

Data Index: 375535 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3876. Min Act: -0.0001

Data Index: 632725 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3730. Min Act: -0.0001

Data Index: 1241344 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3378. Min Act: -0.0001

Data Index: 1002820 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3476. Min Act: -0.0001

Data Index: 1078394 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4558. Min Act: -0.0001

Data Index: 624345 (C4 (Web Text))

Max Activating Token Index: 772