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

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

Neuron 3717 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: 2.4084. Min Range: -2.4084

Max Act: 2.4084. Min Act: -0.0000

Data Index: 39959 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 2.4084. Min Range: -2.4084

Max Act: 2.2094. Min Act: -0.0000

Data Index: 1317735 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.7348. Min Act: -0.0000

Data Index: 385484 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.6638. Min Act: -0.0000

Data Index: 1307633 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.5193. Min Act: -0.0000

Data Index: 1113946 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.4200. Min Act: -0.0000

Data Index: 1074421 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.4712. Min Act: -0.0000

Data Index: 500066 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.3646. Min Act: -0.0000

Data Index: 214064 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.2465. Min Act: -0.0000

Data Index: 537694 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.4104. Min Act: -0.0000

Data Index: 1169183 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.3025. Min Act: -0.0000

Data Index: 932030 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.2317. Min Act: -0.0000

Data Index: 1094065 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.2120. Min Act: -0.0000

Data Index: 287920 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.2013. Min Act: -0.0000

Data Index: 690039 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.1889. Min Act: -0.0000

Data Index: 102659 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.1482. Min Act: -0.0000

Data Index: 796488 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 2.4084. Min Range: -2.4084

Max Act: 0.8347. Min Act: -0.0000

Data Index: 829887 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.1069. Min Act: -0.0000

Data Index: 16153 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.0712. Min Act: -0.0000

Data Index: 487595 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 2.4084. Min Range: -2.4084

Max Act: 1.1524. Min Act: -0.0000

Data Index: 79812 (C4 (Web Text))

Max Activating Token Index: 947