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

Dataset: The Pile

Neuron 1634 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.1922. Min Act: -0.0000

Data Index: 399798 (The Pile)

Max Activating Token Index: 351

Text #1

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.1512. Min Act: -0.0000

Data Index: 266866 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.2003. Min Act: -0.0000

Data Index: 991602 (The Pile)

Max Activating Token Index: 620

Text #3

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.1918. Min Act: -0.0000

Data Index: 46768 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0756. Min Act: -0.0000

Data Index: 328493 (The Pile)

Max Activating Token Index: 942

Text #5

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.1147. Min Act: -0.0000

Data Index: 1306793 (The Pile)

Max Activating Token Index: 450

Text #6

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0559. Min Act: -0.0000

Data Index: 1729146 (The Pile)

Max Activating Token Index: 404

Text #7

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.1056. Min Act: -0.0000

Data Index: 1625906 (The Pile)

Max Activating Token Index: 75

Text #8

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0972. Min Act: -0.0000

Data Index: 1322679 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.1523. Min Act: -0.0000

Data Index: 1249546 (The Pile)

Max Activating Token Index: 707

Text #10

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0667. Min Act: -0.0000

Data Index: 1789069 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1623950 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0612. Min Act: -0.0000

Data Index: 974095 (The Pile)

Max Activating Token Index: 378

Text #13

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0541. Min Act: -0.0000

Data Index: 299435 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1908936 (The Pile)

Max Activating Token Index: 822

Text #15

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1837718 (The Pile)

Max Activating Token Index: 545

Text #16

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0113. Min Act: -0.0000

Data Index: 1453895 (The Pile)

Max Activating Token Index: 459

Text #17

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0364. Min Act: -0.0000

Data Index: 520522 (The Pile)

Max Activating Token Index: 124

Text #18

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9667. Min Act: -0.0000

Data Index: 1401021 (The Pile)

Max Activating Token Index: 835

Text #19

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9403. Min Act: -0.0000

Data Index: 1953224 (The Pile)

Max Activating Token Index: 338