Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 458 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.7285. Min Act: -0.0001

Data Index: 313810 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6478. Min Act: -0.0001

Data Index: 970276 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.7339. Min Act: -0.0001

Data Index: 532170 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.7941. Min Act: -0.0000

Data Index: 684299 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.7254. Min Act: -0.0000

Data Index: 514810 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6863. Min Act: -0.0001

Data Index: 552831 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6602. Min Act: -0.0000

Data Index: 641851 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.7008. Min Act: -0.0000

Data Index: 852742 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6755. Min Act: -0.0001

Data Index: 394132 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.7166. Min Act: -0.0001

Data Index: 966573 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6619. Min Act: -0.0000

Data Index: 535891 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6370. Min Act: -0.0001

Data Index: 1008438 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.7266. Min Act: -0.0000

Data Index: 163747 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6532. Min Act: -0.0000

Data Index: 171000 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6458. Min Act: -0.0001

Data Index: 511162 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6018. Min Act: -0.0001

Data Index: 654849 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5796. Min Act: -0.0000

Data Index: 616806 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6379. Min Act: -0.0000

Data Index: 227715 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6256. Min Act: -0.0000

Data Index: 413099 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6287. Min Act: -0.0001

Data Index: 1200847 (C4 (Web Text))

Max Activating Token Index: 53