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

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

Neuron 28 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1625. Min Range: -1.1625

Max Act: 1.1625. Min Act: -0.0000

Data Index: 1052180 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 1.1625. Min Range: -1.1625

Max Act: 1.0325. Min Act: -0.0000

Data Index: 950683 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.9985. Min Act: -0.0000

Data Index: 1035240 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.9834. Min Act: -0.0000

Data Index: 356287 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.9112. Min Act: -0.0000

Data Index: 369058 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1240166 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.8690. Min Act: -0.0000

Data Index: 159801 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7650. Min Act: -0.0000

Data Index: 64584 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.8859. Min Act: -0.0000

Data Index: 18878 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1228461 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.8011. Min Act: -0.0000

Data Index: 953047 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7696. Min Act: -0.0000

Data Index: 307662 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1054146 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.8074. Min Act: -0.0000

Data Index: 233822 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7821. Min Act: -0.0000

Data Index: 1042069 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1150901 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7437. Min Act: -0.0000

Data Index: 4163 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1544855 (Python Code)

Max Activating Token Index: 345

Text #18

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7497. Min Act: -0.0000

Data Index: 208461 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7470. Min Act: -0.0000

Data Index: 675276 (C4 (Web Text))

Max Activating Token Index: 489