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

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

Neuron 1841 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0711. Min Range: -1.0711

Max Act: 1.0711. Min Act: -0.0000

Data Index: 672716 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 1.0711. Min Range: -1.0711

Max Act: 1.0623. Min Act: -0.0000

Data Index: 852936 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.9106. Min Act: -0.0000

Data Index: 421627 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.9990. Min Act: -0.0000

Data Index: 1124069 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.9661. Min Act: -0.0000

Data Index: 891296 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.9272. Min Act: -0.0000

Data Index: 331196 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.9834. Min Act: -0.0000

Data Index: 1309176 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1005929 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8364. Min Act: -0.0000

Data Index: 1106294 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.9459. Min Act: -0.0000

Data Index: 58028 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1072800 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8804. Min Act: -0.0000

Data Index: 882850 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1119930 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8341. Min Act: -0.0000

Data Index: 160170 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8614. Min Act: -0.0000

Data Index: 217430 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8111. Min Act: -0.0000

Data Index: 1489161 (Python Code)

Max Activating Token Index: 1015

Text #16

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.7640. Min Act: -0.0000

Data Index: 280917 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.7863. Min Act: -0.0000

Data Index: 308774 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8311. Min Act: -0.0000

Data Index: 326511 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.7802. Min Act: -0.0000

Data Index: 631084 (C4 (Web Text))

Max Activating Token Index: 31