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

Dataset: The Pile

Neuron 2956 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.4433. Min Act: -0.0000

Data Index: 1009966 (The Pile)

Max Activating Token Index: 755

Text #1

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.2180. Min Act: -0.0000

Data Index: 933898 (The Pile)

Max Activating Token Index: 821

Text #2

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.3597. Min Act: -0.0000

Data Index: 565669 (The Pile)

Max Activating Token Index: 292

Text #3

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1810. Min Act: -0.0000

Data Index: 1348330 (The Pile)

Max Activating Token Index: 439

Text #4

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1353. Min Act: -0.0000

Data Index: 1140416 (The Pile)

Max Activating Token Index: 949

Text #5

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1553. Min Act: -0.0000

Data Index: 156809 (The Pile)

Max Activating Token Index: 705

Text #6

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1542. Min Act: -0.0000

Data Index: 60097 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1162. Min Act: -0.0000

Data Index: 589106 (The Pile)

Max Activating Token Index: 190

Text #8

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1044. Min Act: -0.0000

Data Index: 459145 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1269318 (The Pile)

Max Activating Token Index: 295

Text #10

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1162. Min Act: -0.0000

Data Index: 1129398 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.0938. Min Act: -0.0000

Data Index: 1175913 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1507. Min Act: -0.0000

Data Index: 1767507 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1411. Min Act: -0.0000

Data Index: 1061684 (The Pile)

Max Activating Token Index: 793

Text #14

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1015375 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.0279. Min Act: -0.0000

Data Index: 379538 (The Pile)

Max Activating Token Index: 909

Text #16

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.0765. Min Act: -0.0000

Data Index: 532035 (The Pile)

Max Activating Token Index: 939

Text #17

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1069. Min Act: -0.0000

Data Index: 865695 (The Pile)

Max Activating Token Index: 189

Text #18

Max Range: 1.4433. Min Range: -1.4433

Max Act: 0.9671. Min Act: -0.0000

Data Index: 31626 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.0284. Min Act: -0.0000

Data Index: 331878 (The Pile)

Max Activating Token Index: 600