Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2429 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1891. Min Act: -0.0001

Data Index: 1358129 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1918. Min Act: -0.0001

Data Index: 14645 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1957. Min Act: -0.0001

Data Index: 586571 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1820. Min Act: -0.0001

Data Index: 1026243 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1825. Min Act: -0.0001

Data Index: 455952 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1848. Min Act: -0.0000

Data Index: 150490 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1656. Min Act: -0.0001

Data Index: 366825 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1837. Min Act: -0.0001

Data Index: 167933 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1638. Min Act: -0.0001

Data Index: 2066 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1585. Min Act: -0.0000

Data Index: 824774 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1580. Min Act: -0.0000

Data Index: 538803 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1512. Min Act: -0.0000

Data Index: 602271 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1546. Min Act: -0.0000

Data Index: 96158 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1539. Min Act: -0.0000

Data Index: 413830 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1528. Min Act: -0.0000

Data Index: 721732 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1544. Min Act: -0.0000

Data Index: 231108 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1651. Min Act: -0.0000

Data Index: 609096 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1402. Min Act: -0.0000

Data Index: 1322524 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1501. Min Act: -0.0001

Data Index: 370922 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1480. Min Act: -0.0000

Data Index: 717339 (C4 (Web Text))

Max Activating Token Index: 450