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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 283 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.7013. Min Act: -0.0000

Data Index: 1027542 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5962. Min Act: -0.0000

Data Index: 543330 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.3550. Min Act: -0.0000

Data Index: 1057282 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.4220. Min Act: 0.0000

Data Index: 597467 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.3567. Min Act: -0.0000

Data Index: 573825 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.1220. Min Act: -0.0000

Data Index: 319531 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 3.7013. Min Range: -3.7013

Max Act: 2.9094. Min Act: -0.0000

Data Index: 490570 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 3.7013. Min Range: -3.7013

Max Act: 2.7710. Min Act: -0.0000

Data Index: 1018384 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 3.7013. Min Range: -3.7013

Max Act: 2.6630. Min Act: -0.0000

Data Index: 476075 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 3.7013. Min Range: -3.7013

Max Act: 2.4676. Min Act: -0.0000

Data Index: 865756 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 3.7013. Min Range: -3.7013

Max Act: 2.5607. Min Act: -0.0000

Data Index: 244073 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 3.7013. Min Range: -3.7013

Max Act: 2.6657. Min Act: -0.0000

Data Index: 1342910 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 3.7013. Min Range: -3.7013

Max Act: 2.4641. Min Act: -0.0000

Data Index: 548972 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 3.7013. Min Range: -3.7013

Max Act: 2.4569. Min Act: -0.0000

Data Index: 1212092 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 3.7013. Min Range: -3.7013

Max Act: 2.5295. Min Act: -0.0000

Data Index: 1199210 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 3.7013. Min Range: -3.7013

Max Act: 2.3863. Min Act: -0.0000

Data Index: 232419 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 3.7013. Min Range: -3.7013

Max Act: 2.3808. Min Act: -0.0000

Data Index: 913259 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 3.7013. Min Range: -3.7013

Max Act: 2.2872. Min Act: -0.0000

Data Index: 1142594 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 3.7013. Min Range: -3.7013

Max Act: 2.1509. Min Act: 0.0000

Data Index: 1303860 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 3.7013. Min Range: -3.7013

Max Act: 2.2772. Min Act: 0.0001

Data Index: 887276 (C4 (Web Text))

Max Activating Token Index: 540