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

Dataset: The Pile

Neuron 4694 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0904. Min Range: -1.0904

Max Act: 1.0783. Min Act: -0.0000

Data Index: 1877277 (The Pile)

Max Activating Token Index: 998

Text #1

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.9900. Min Act: -0.0000

Data Index: 69334 (The Pile)

Max Activating Token Index: 632

Text #2

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.9959. Min Act: 0.0000

Data Index: 418790 (The Pile)

Max Activating Token Index: 293

Text #3

Max Range: 1.0904. Min Range: -1.0904

Max Act: 1.0904. Min Act: -0.0000

Data Index: 1170312 (The Pile)

Max Activating Token Index: 625

Text #4

Max Range: 1.0904. Min Range: -1.0904

Max Act: 1.0671. Min Act: -0.0000

Data Index: 1760829 (The Pile)

Max Activating Token Index: 465

Text #5

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8308. Min Act: -0.0000

Data Index: 676475 (The Pile)

Max Activating Token Index: 981

Text #6

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.9307. Min Act: -0.0000

Data Index: 117795 (The Pile)

Max Activating Token Index: 587

Text #7

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.9590. Min Act: 0.0000

Data Index: 1215260 (The Pile)

Max Activating Token Index: 231

Text #8

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8756. Min Act: -0.0000

Data Index: 410222 (The Pile)

Max Activating Token Index: 365

Text #9

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1590255 (The Pile)

Max Activating Token Index: 810

Text #10

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1391864 (The Pile)

Max Activating Token Index: 105

Text #11

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8471. Min Act: -0.0000

Data Index: 536415 (The Pile)

Max Activating Token Index: 909

Text #12

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1097300 (The Pile)

Max Activating Token Index: 465

Text #13

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8271. Min Act: -0.0000

Data Index: 612303 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1735704 (The Pile)

Max Activating Token Index: 389

Text #15

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1212435 (The Pile)

Max Activating Token Index: 680

Text #16

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7342. Min Act: -0.0000

Data Index: 143159 (The Pile)

Max Activating Token Index: 615

Text #17

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7796. Min Act: -0.0000

Data Index: 52229 (The Pile)

Max Activating Token Index: 518

Text #18

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1565955 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1177680 (The Pile)

Max Activating Token Index: 783