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

Dataset: The Pile

Neuron 1616 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: 1.2723. Min Range: -1.2723

Max Act: 1.2723. Min Act: -0.0000

Data Index: 1523235 (The Pile)

Max Activating Token Index: 529

Text #1

Max Range: 1.2723. Min Range: -1.2723

Max Act: 1.0260. Min Act: -0.0000

Data Index: 1140001 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9962. Min Act: -0.0000

Data Index: 376396 (The Pile)

Max Activating Token Index: 947

Text #3

Max Range: 1.2723. Min Range: -1.2723

Max Act: 1.2101. Min Act: -0.0000

Data Index: 1409113 (The Pile)

Max Activating Token Index: 177

Text #4

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9460. Min Act: -0.0000

Data Index: 25256 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 1.2723. Min Range: -1.2723

Max Act: 1.0859. Min Act: -0.0000

Data Index: 1135240 (The Pile)

Max Activating Token Index: 362

Text #6

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9889. Min Act: -0.0000

Data Index: 1864058 (The Pile)

Max Activating Token Index: 128

Text #7

Max Range: 1.2723. Min Range: -1.2723

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1567701 (The Pile)

Max Activating Token Index: 391

Text #8

Max Range: 1.2723. Min Range: -1.2723

Max Act: 1.0191. Min Act: -0.0000

Data Index: 1138788 (The Pile)

Max Activating Token Index: 323

Text #9

Max Range: 1.2723. Min Range: -1.2723

Max Act: 1.1345. Min Act: -0.0000

Data Index: 1127497 (The Pile)

Max Activating Token Index: 578

Text #10

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1474571 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9999. Min Act: -0.0000

Data Index: 581434 (The Pile)

Max Activating Token Index: 468

Text #12

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1273478 (The Pile)

Max Activating Token Index: 726

Text #13

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1986456 (The Pile)

Max Activating Token Index: 83

Text #14

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9419. Min Act: -0.0000

Data Index: 248361 (The Pile)

Max Activating Token Index: 956

Text #15

Max Range: 1.2723. Min Range: -1.2723

Max Act: 1.0266. Min Act: -0.0000

Data Index: 461245 (The Pile)

Max Activating Token Index: 59

Text #16

Max Range: 1.2723. Min Range: -1.2723

Max Act: 1.0482. Min Act: -0.0000

Data Index: 534092 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.8602. Min Act: -0.0000

Data Index: 1367182 (The Pile)

Max Activating Token Index: 777

Text #18

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9441. Min Act: -0.0000

Data Index: 1841508 (The Pile)

Max Activating Token Index: 961

Text #19

Max Range: 1.2723. Min Range: -1.2723

Max Act: 0.9234. Min Act: -0.0000

Data Index: 191848 (The Pile)

Max Activating Token Index: 277