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

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

Neuron 3248 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1957. Min Act: -0.0002

Data Index: 1288071 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1824. Min Act: -0.0002

Data Index: 244869 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1881. Min Act: -0.0002

Data Index: 583901 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1806. Min Act: -0.0002

Data Index: 1216089 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1836. Min Act: -0.0002

Data Index: 479699 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1783. Min Act: -0.0002

Data Index: 147653 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1607. Min Act: -0.0002

Data Index: 28347 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1747. Min Act: -0.0002

Data Index: 146289 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1673. Min Act: -0.0002

Data Index: 572139 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1664. Min Act: -0.0002

Data Index: 537763 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1803. Min Act: -0.0002

Data Index: 1246762 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1441. Min Act: -0.0002

Data Index: 618991 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1476. Min Act: -0.0002

Data Index: 698304 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1600. Min Act: -0.0002

Data Index: 678799 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1555. Min Act: -0.0002

Data Index: 1003164 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1347. Min Act: -0.0002

Data Index: 859512 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1503. Min Act: -0.0002

Data Index: 1272870 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1447. Min Act: -0.0002

Data Index: 1218623 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1519. Min Act: -0.0002

Data Index: 165030 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1414. Min Act: -0.0002

Data Index: 1292652 (C4 (Web Text))

Max Activating Token Index: 580