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

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

Neuron 3106 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0722. Min Act: -0.0000

Data Index: 165018 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1274291 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0662. Min Act: -0.0001

Data Index: 627881 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0782. Min Act: -0.0001

Data Index: 909972 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0617. Min Act: -0.0001

Data Index: 232673 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0590. Min Act: -0.0000

Data Index: 350515 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0666. Min Act: -0.0001

Data Index: 1200711 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1245234 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0618. Min Act: -0.0001

Data Index: 9667 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0613. Min Act: -0.0000

Data Index: 620231 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0644. Min Act: -0.0000

Data Index: 508029 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0624. Min Act: -0.0000

Data Index: 604892 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0579. Min Act: -0.0001

Data Index: 445442 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0532. Min Act: -0.0001

Data Index: 345214 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1317889 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0524. Min Act: -0.0000

Data Index: 37230 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0584. Min Act: -0.0001

Data Index: 1040123 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1200341 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0554. Min Act: -0.0000

Data Index: 870683 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0540. Min Act: -0.0001

Data Index: 779370 (C4 (Web Text))

Max Activating Token Index: 268