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

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

Neuron 3450 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6889. Min Act: -0.0000

Data Index: 695426 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6589. Min Act: -0.0000

Data Index: 525344 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5840. Min Act: -0.0000

Data Index: 741534 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5647. Min Act: -0.0000

Data Index: 677840 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5996. Min Act: -0.0000

Data Index: 873506 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6167. Min Act: -0.0000

Data Index: 514386 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5335. Min Act: -0.0000

Data Index: 689924 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5621. Min Act: -0.0000

Data Index: 382929 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1011442 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1325885 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5626. Min Act: -0.0000

Data Index: 237447 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5557. Min Act: -0.0000

Data Index: 182342 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5572. Min Act: -0.0000

Data Index: 61586 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5458. Min Act: -0.0000

Data Index: 630869 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5720. Min Act: -0.0000

Data Index: 635891 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5472. Min Act: -0.0000

Data Index: 33644 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5514. Min Act: -0.0000

Data Index: 886624 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.4598. Min Act: -0.0000

Data Index: 280968 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1200463 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5061. Min Act: -0.0000

Data Index: 348314 (C4 (Web Text))

Max Activating Token Index: 943