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

Dataset: The Pile

Neuron 4245 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: 0.8223. Min Range: -0.8223

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1333389 (The Pile)

Max Activating Token Index: 247

Text #1

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.7091. Min Act: -0.0000

Data Index: 1238193 (The Pile)

Max Activating Token Index: 307

Text #2

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6424. Min Act: -0.0000

Data Index: 610218 (The Pile)

Max Activating Token Index: 807

Text #3

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6788. Min Act: -0.0000

Data Index: 511386 (The Pile)

Max Activating Token Index: 462

Text #4

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1986414 (The Pile)

Max Activating Token Index: 183

Text #5

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6450. Min Act: -0.0000

Data Index: 513107 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5676. Min Act: -0.0000

Data Index: 772331 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1845389 (The Pile)

Max Activating Token Index: 18

Text #8

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5851. Min Act: -0.0000

Data Index: 170419 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5582. Min Act: -0.0001

Data Index: 1686914 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1810098 (The Pile)

Max Activating Token Index: 899

Text #11

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5606. Min Act: -0.0000

Data Index: 920356 (The Pile)

Max Activating Token Index: 194

Text #12

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1216899 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5303. Min Act: -0.0000

Data Index: 579743 (The Pile)

Max Activating Token Index: 98

Text #14

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1460157 (The Pile)

Max Activating Token Index: 406

Text #15

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1070554 (The Pile)

Max Activating Token Index: 917

Text #16

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6057. Min Act: -0.0000

Data Index: 1014138 (The Pile)

Max Activating Token Index: 824

Text #17

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1473383 (The Pile)

Max Activating Token Index: 530

Text #18

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1275301 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5021. Min Act: -0.0000

Data Index: 489322 (The Pile)

Max Activating Token Index: 469