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

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

Neuron 4654 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: 0.9928. Min Range: -0.9928

Max Act: 0.9928. Min Act: -0.0001

Data Index: 539540 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.9363. Min Act: -0.0001

Data Index: 971622 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.9350. Min Act: -0.0001

Data Index: 868114 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8914. Min Act: -0.0001

Data Index: 774998 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.9059. Min Act: -0.0002

Data Index: 321697 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8808. Min Act: -0.0001

Data Index: 845144 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8932. Min Act: -0.0001

Data Index: 269636 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8709. Min Act: -0.0001

Data Index: 890517 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8797. Min Act: -0.0001

Data Index: 58599 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8733. Min Act: -0.0001

Data Index: 457895 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8800. Min Act: -0.0001

Data Index: 441577 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8659. Min Act: -0.0001

Data Index: 637262 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8552. Min Act: -0.0001

Data Index: 678626 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8508. Min Act: -0.0001

Data Index: 296860 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8567. Min Act: -0.0001

Data Index: 1319847 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8344. Min Act: -0.0001

Data Index: 532036 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8517. Min Act: -0.0001

Data Index: 268931 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8425. Min Act: -0.0001

Data Index: 840878 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8525. Min Act: -0.0001

Data Index: 96828 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8543. Min Act: -0.0001

Data Index: 1236193 (C4 (Web Text))

Max Activating Token Index: 117