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

Dataset: The Pile

Neuron 4465 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: 1.1679. Min Range: -1.1679

Max Act: 1.1679. Min Act: -0.0000

Data Index: 602911 (The Pile)

Max Activating Token Index: 366

Text #1

Max Range: 1.1679. Min Range: -1.1679

Max Act: 1.0890. Min Act: -0.0000

Data Index: 1314917 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.9003. Min Act: -0.0000

Data Index: 1886779 (The Pile)

Max Activating Token Index: 525

Text #3

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.9183. Min Act: -0.0000

Data Index: 110406 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 1.1679. Min Range: -1.1679

Max Act: 1.0067. Min Act: -0.0000

Data Index: 191130 (The Pile)

Max Activating Token Index: 890

Text #5

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.8233. Min Act: -0.0000

Data Index: 869728 (The Pile)

Max Activating Token Index: 1001

Text #6

Max Range: 1.1679. Min Range: -1.1679

Max Act: 1.0202. Min Act: -0.0000

Data Index: 807545 (The Pile)

Max Activating Token Index: 902

Text #7

Max Range: 1.1679. Min Range: -1.1679

Max Act: 1.0056. Min Act: -0.0000

Data Index: 504318 (The Pile)

Max Activating Token Index: 921

Text #8

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.9489. Min Act: -0.0000

Data Index: 275293 (The Pile)

Max Activating Token Index: 674

Text #9

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.9185. Min Act: -0.0000

Data Index: 948432 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1866817 (The Pile)

Max Activating Token Index: 886

Text #11

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1911378 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1828090 (The Pile)

Max Activating Token Index: 803

Text #13

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1399086 (The Pile)

Max Activating Token Index: 558

Text #14

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.8425. Min Act: -0.0000

Data Index: 663766 (The Pile)

Max Activating Token Index: 994

Text #15

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1225222 (The Pile)

Max Activating Token Index: 663

Text #16

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.7727. Min Act: -0.0000

Data Index: 54106 (The Pile)

Max Activating Token Index: 839

Text #17

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1990384 (The Pile)

Max Activating Token Index: 614

Text #18

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1294114 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1212791 (The Pile)

Max Activating Token Index: 855