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

Dataset: The Pile

Neuron 2121 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3790. Min Range: -1.3790

Max Act: 1.3790. Min Act: -0.0000

Data Index: 999895 (The Pile)

Max Activating Token Index: 266

Text #1

Max Range: 1.3790. Min Range: -1.3790

Max Act: 1.1300. Min Act: -0.0000

Data Index: 256007 (The Pile)

Max Activating Token Index: 773

Text #2

Max Range: 1.3790. Min Range: -1.3790

Max Act: 1.1637. Min Act: -0.0000

Data Index: 1996465 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 1.3790. Min Range: -1.3790

Max Act: 1.1268. Min Act: -0.0000

Data Index: 1180765 (The Pile)

Max Activating Token Index: 916

Text #4

Max Range: 1.3790. Min Range: -1.3790

Max Act: 1.1592. Min Act: -0.0000

Data Index: 586223 (The Pile)

Max Activating Token Index: 806

Text #5

Max Range: 1.3790. Min Range: -1.3790

Max Act: 1.1447. Min Act: -0.0000

Data Index: 1442678 (The Pile)

Max Activating Token Index: 903

Text #6

Max Range: 1.3790. Min Range: -1.3790

Max Act: 1.0554. Min Act: -0.0000

Data Index: 1579696 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 1.3790. Min Range: -1.3790

Max Act: 0.9460. Min Act: -0.0000

Data Index: 30418 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 1.3790. Min Range: -1.3790

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1939678 (The Pile)

Max Activating Token Index: 362

Text #9

Max Range: 1.3790. Min Range: -1.3790

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1079344 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 1.3790. Min Range: -1.3790

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1006069 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 1.3790. Min Range: -1.3790

Max Act: 0.9707. Min Act: -0.0000

Data Index: 4476 (The Pile)

Max Activating Token Index: 275

Text #12

Max Range: 1.3790. Min Range: -1.3790

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1104936 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 1.3790. Min Range: -1.3790

Max Act: 0.8663. Min Act: -0.0000

Data Index: 1568972 (The Pile)

Max Activating Token Index: 791

Text #14

Max Range: 1.3790. Min Range: -1.3790

Max Act: 0.9323. Min Act: -0.0000

Data Index: 889022 (The Pile)

Max Activating Token Index: 189

Text #15

Max Range: 1.3790. Min Range: -1.3790

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1283710 (The Pile)

Max Activating Token Index: 818

Text #16

Max Range: 1.3790. Min Range: -1.3790

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1701076 (The Pile)

Max Activating Token Index: 89

Text #17

Max Range: 1.3790. Min Range: -1.3790

Max Act: 0.9110. Min Act: -0.0000

Data Index: 27417 (The Pile)

Max Activating Token Index: 349

Text #18

Max Range: 1.3790. Min Range: -1.3790

Max Act: 0.9539. Min Act: -0.0000

Data Index: 549211 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 1.3790. Min Range: -1.3790

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1123882 (The Pile)

Max Activating Token Index: 600