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

Dataset: The Pile

Neuron 522 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: 0.4394. Min Range: -0.4394

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1120892 (The Pile)

Max Activating Token Index: 885

Text #1

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1955756 (The Pile)

Max Activating Token Index: 352

Text #2

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2680. Min Act: -0.0000

Data Index: 435390 (The Pile)

Max Activating Token Index: 653

Text #3

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2329. Min Act: -0.0000

Data Index: 563640 (The Pile)

Max Activating Token Index: 886

Text #4

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2215. Min Act: -0.0000

Data Index: 752025 (The Pile)

Max Activating Token Index: 902

Text #5

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1684571 (The Pile)

Max Activating Token Index: 711

Text #6

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2623. Min Act: -0.0000

Data Index: 749089 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1033588 (The Pile)

Max Activating Token Index: 189

Text #8

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1757146 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1181922 (The Pile)

Max Activating Token Index: 888

Text #10

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1153061 (The Pile)

Max Activating Token Index: 373

Text #11

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1256120 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2337. Min Act: -0.0000

Data Index: 797902 (The Pile)

Max Activating Token Index: 481

Text #13

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1575221 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2067. Min Act: -0.0000

Data Index: 245841 (The Pile)

Max Activating Token Index: 936

Text #15

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1796043 (The Pile)

Max Activating Token Index: 700

Text #16

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2240. Min Act: -0.0000

Data Index: 797226 (The Pile)

Max Activating Token Index: 954

Text #17

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1294581 (The Pile)

Max Activating Token Index: 1013

Text #18

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.1815. Min Act: -0.0000

Data Index: 413446 (The Pile)

Max Activating Token Index: 905

Text #19

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.2083. Min Act: -0.0000

Data Index: 636148 (The Pile)

Max Activating Token Index: 676