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

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

Neuron 4866 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: 0.1353. Min Range: -0.1353

Max Act: 0.1353. Min Act: -0.0001

Data Index: 61168 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1020. Min Act: -0.0001

Data Index: 1243779 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1225369 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1337664 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0910. Min Act: -0.0001

Data Index: 364474 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0877. Min Act: -0.0001

Data Index: 740594 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0886. Min Act: -0.0001

Data Index: 8879 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0818. Min Act: -0.0001

Data Index: 511217 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0893. Min Act: -0.0001

Data Index: 977063 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1093353 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0830. Min Act: -0.0001

Data Index: 717354 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0779. Min Act: -0.0001

Data Index: 394633 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0711. Min Act: -0.0001

Data Index: 312493 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1229178 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0795. Min Act: -0.0001

Data Index: 778068 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0813. Min Act: -0.0001

Data Index: 46491 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0733. Min Act: -0.0001

Data Index: 722489 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0801. Min Act: -0.0001

Data Index: 935795 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0734. Min Act: -0.0001

Data Index: 747708 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0763. Min Act: -0.0001

Data Index: 428924 (C4 (Web Text))

Max Activating Token Index: 248