Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2466 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0855. Min Range: -1.0855

Max Act: 1.0855. Min Act: -0.0000

Data Index: 272246 (The Pile)

Max Activating Token Index: 179

Text #1

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1151977 (The Pile)

Max Activating Token Index: 141

Text #2

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.6603. Min Act: -0.0000

Data Index: 913468 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1854251 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1841363 (The Pile)

Max Activating Token Index: 947

Text #5

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1963869 (The Pile)

Max Activating Token Index: 827

Text #6

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.4928. Min Act: -0.0000

Data Index: 56870 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1968212 (The Pile)

Max Activating Token Index: 911

Text #8

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.5746. Min Act: -0.0000

Data Index: 1641203 (The Pile)

Max Activating Token Index: 204

Text #9

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1375152 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1695717 (The Pile)

Max Activating Token Index: 371

Text #11

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.5404. Min Act: -0.0000

Data Index: 1025585 (The Pile)

Max Activating Token Index: 1008

Text #12

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1615111 (The Pile)

Max Activating Token Index: 482

Text #13

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1143552 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.5150. Min Act: -0.0000

Data Index: 658400 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.5428. Min Act: -0.0000

Data Index: 251981 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1118003 (The Pile)

Max Activating Token Index: 845

Text #17

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.4446. Min Act: -0.0000

Data Index: 701683 (The Pile)

Max Activating Token Index: 878

Text #18

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1467613 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.4793. Min Act: -0.0000

Data Index: 814229 (The Pile)

Max Activating Token Index: 956