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

Dataset: The Pile

Neuron 2997 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: 1.3281. Min Range: -1.3281

Max Act: 1.3281. Min Act: -0.0000

Data Index: 410930 (The Pile)

Max Activating Token Index: 92

Text #1

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1258420 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2658. Min Act: -0.0000

Data Index: 1587658 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1843737 (The Pile)

Max Activating Token Index: 194

Text #4

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.0925. Min Act: -0.0000

Data Index: 1876081 (The Pile)

Max Activating Token Index: 142

Text #5

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1133928 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1149. Min Act: -0.0000

Data Index: 1520683 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1376. Min Act: -0.0000

Data Index: 570235 (The Pile)

Max Activating Token Index: 964

Text #8

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.0387. Min Act: -0.0000

Data Index: 717023 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1253. Min Act: -0.0000

Data Index: 1596995 (The Pile)

Max Activating Token Index: 79

Text #10

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1198. Min Act: -0.0000

Data Index: 1130216 (The Pile)

Max Activating Token Index: 89

Text #11

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1728. Min Act: -0.0000

Data Index: 1432404 (The Pile)

Max Activating Token Index: 938

Text #12

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.0399. Min Act: -0.0000

Data Index: 703480 (The Pile)

Max Activating Token Index: 732

Text #13

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.0495. Min Act: -0.0000

Data Index: 501838 (The Pile)

Max Activating Token Index: 344

Text #14

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1114. Min Act: -0.0000

Data Index: 1131541 (The Pile)

Max Activating Token Index: 555

Text #15

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.0422. Min Act: -0.0000

Data Index: 972587 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.9833. Min Act: -0.0000

Data Index: 1530894 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.0261. Min Act: -0.0000

Data Index: 1517646 (The Pile)

Max Activating Token Index: 12

Text #18

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.0222. Min Act: -0.0000

Data Index: 1477064 (The Pile)

Max Activating Token Index: 20

Text #19

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.9558. Min Act: -0.0000

Data Index: 533689 (The Pile)

Max Activating Token Index: 63