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

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

Neuron 3579 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: 1.4437. Min Range: -1.4437

Max Act: 1.4437. Min Act: -0.0001

Data Index: 253447 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.2029. Min Act: -0.0001

Data Index: 1144014 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.1520. Min Act: -0.0001

Data Index: 1292205 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.0674. Min Act: -0.0001

Data Index: 742729 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.0171. Min Act: -0.0001

Data Index: 322704 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.0096. Min Act: -0.0001

Data Index: 911443 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.0359. Min Act: -0.0001

Data Index: 1173426 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.0007. Min Act: -0.0001

Data Index: 968805 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.0338. Min Act: -0.0001

Data Index: 869830 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.8796. Min Act: -0.0001

Data Index: 1289922 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.9569. Min Act: -0.0001

Data Index: 211110 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.1168. Min Act: -0.0001

Data Index: 432767 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.8210. Min Act: -0.0001

Data Index: 1253922 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.8853. Min Act: -0.0001

Data Index: 55013 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.7587. Min Act: -0.0001

Data Index: 1047838 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.8865. Min Act: -0.0001

Data Index: 632228 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.9520. Min Act: -0.0001

Data Index: 857814 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.7916. Min Act: -0.0001

Data Index: 1021634 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.0303. Min Act: -0.0001

Data Index: 1176980 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 1.4437. Min Range: -1.4437

Max Act: 0.8647. Min Act: -0.0001

Data Index: 553372 (C4 (Web Text))

Max Activating Token Index: 472