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

Dataset: The Pile

Neuron 4937 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0074. Min Range: -1.0074

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1265506 (The Pile)

Max Activating Token Index: 368

Text #1

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.9197. Min Act: -0.0000

Data Index: 882512 (The Pile)

Max Activating Token Index: 375

Text #2

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.7371. Min Act: -0.0000

Data Index: 1678966 (The Pile)

Max Activating Token Index: 309

Text #3

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.7262. Min Act: -0.0000

Data Index: 941514 (The Pile)

Max Activating Token Index: 831

Text #4

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1921822 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1777838 (The Pile)

Max Activating Token Index: 235

Text #6

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6964. Min Act: -0.0000

Data Index: 71687 (The Pile)

Max Activating Token Index: 374

Text #7

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6861. Min Act: 0.0000

Data Index: 1620205 (The Pile)

Max Activating Token Index: 950

Text #8

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6874. Min Act: 0.0000

Data Index: 1553287 (The Pile)

Max Activating Token Index: 432

Text #9

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6854. Min Act: -0.0000

Data Index: 605490 (The Pile)

Max Activating Token Index: 91

Text #10

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1024464 (The Pile)

Max Activating Token Index: 935

Text #11

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6661. Min Act: -0.0000

Data Index: 122554 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6615. Min Act: -0.0000

Data Index: 577854 (The Pile)

Max Activating Token Index: 842

Text #13

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1541402 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1401985 (The Pile)

Max Activating Token Index: 812

Text #15

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6395. Min Act: 0.0000

Data Index: 69301 (The Pile)

Max Activating Token Index: 902

Text #16

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1728955 (The Pile)

Max Activating Token Index: 77

Text #17

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1715695 (The Pile)

Max Activating Token Index: 375

Text #18

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1805672 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6310. Min Act: -0.0000

Data Index: 199070 (The Pile)

Max Activating Token Index: 51