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

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

Neuron 5195 in Layer 0

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: 0.0873. Min Range: -0.0873

Max Act: 0.0873. Min Act: -0.0001

Data Index: 75916 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0801. Min Act: -0.0001

Data Index: 527439 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1298391 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0780. Min Act: -0.0001

Data Index: 705884 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0779. Min Act: -0.0001

Data Index: 152749 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1211211 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1302130 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0767. Min Act: -0.0001

Data Index: 1571826 (Python Code)

Max Activating Token Index: 689

Text #8

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0748. Min Act: -0.0001

Data Index: 352052 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0776. Min Act: -0.0002

Data Index: 178093 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0772. Min Act: -0.0001

Data Index: 168273 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0760. Min Act: -0.0001

Data Index: 239859 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0752. Min Act: -0.0001

Data Index: 375144 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0753. Min Act: -0.0001

Data Index: 720391 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0752. Min Act: -0.0001

Data Index: 705672 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0750. Min Act: -0.0001

Data Index: 356824 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1105851 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1318984 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0746. Min Act: -0.0001

Data Index: 456546 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0761. Min Act: -0.0001

Data Index: 301420 (C4 (Web Text))

Max Activating Token Index: 942