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

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

Neuron 1553 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0836. Min Act: -0.0002

Data Index: 773762 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0815. Min Act: -0.0002

Data Index: 544956 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0806. Min Act: -0.0002

Data Index: 147205 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0815. Min Act: -0.0002

Data Index: 685604 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0776. Min Act: -0.0002

Data Index: 599543 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1614415 (Python Code)

Max Activating Token Index: 643

Text #6

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0794. Min Act: -0.0002

Data Index: 541959 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1167658 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1051462 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0767. Min Act: -0.0002

Data Index: 678043 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0752. Min Act: -0.0002

Data Index: 811818 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1365950 (Python Code)

Max Activating Token Index: 89

Text #12

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0730. Min Act: -0.0002

Data Index: 266730 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1241924 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0742. Min Act: -0.0002

Data Index: 926062 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0718. Min Act: -0.0002

Data Index: 960449 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0729. Min Act: -0.0002

Data Index: 707361 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0731. Min Act: -0.0002

Data Index: 986592 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1243109 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0723. Min Act: -0.0002

Data Index: 669496 (C4 (Web Text))

Max Activating Token Index: 691