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

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

Neuron 3522 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.9049. Min Act: -0.0000

Data Index: 542978 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.6825. Min Act: -0.0000

Data Index: 1655105 (Python Code)

Max Activating Token Index: 424

Text #2

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1496718 (Python Code)

Max Activating Token Index: 492

Text #3

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1597233 (Python Code)

Max Activating Token Index: 489

Text #4

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1403555 (Python Code)

Max Activating Token Index: 710

Text #5

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1359849 (Python Code)

Max Activating Token Index: 845

Text #6

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1570532 (Python Code)

Max Activating Token Index: 380

Text #7

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.5731. Min Act: -0.0000

Data Index: 812644 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.5597. Min Act: -0.0000

Data Index: 66151 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.5169. Min Act: -0.0000

Data Index: 333626 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.5705. Min Act: -0.0000

Data Index: 228255 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.5219. Min Act: -0.0000

Data Index: 808684 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1618598 (Python Code)

Max Activating Token Index: 473

Text #13

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1517736 (Python Code)

Max Activating Token Index: 559

Text #14

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1470927 (Python Code)

Max Activating Token Index: 937

Text #15

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.4869. Min Act: -0.0000

Data Index: 895625 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1157621 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.4828. Min Act: -0.0000

Data Index: 368405 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1549484 (Python Code)

Max Activating Token Index: 161

Text #19

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.4718. Min Act: -0.0000

Data Index: 918114 (C4 (Web Text))

Max Activating Token Index: 297