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

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

Neuron 2743 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3641. Min Range: -2.3641

Max Act: 2.3641. Min Act: -0.0000

Data Index: 72136 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.6064. Min Act: -0.0000

Data Index: 660073 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.7271. Min Act: -0.0000

Data Index: 172849 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.6930. Min Act: -0.0000

Data Index: 167979 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.5654. Min Act: -0.0000

Data Index: 66052 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.6511. Min Act: -0.0000

Data Index: 1306166 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.5608. Min Act: -0.0000

Data Index: 384148 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.4495. Min Act: -0.0000

Data Index: 1074513 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.6255. Min Act: -0.0001

Data Index: 448429 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.5313. Min Act: -0.0001

Data Index: 1029846 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.5839. Min Act: -0.0000

Data Index: 1013751 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.5228. Min Act: -0.0000

Data Index: 297857 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.5698. Min Act: -0.0000

Data Index: 640521 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.6504. Min Act: -0.0000

Data Index: 1005275 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.5372. Min Act: -0.0000

Data Index: 994313 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.4624. Min Act: -0.0000

Data Index: 1134651 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.5224. Min Act: -0.0000

Data Index: 127924 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.3817. Min Act: -0.0000

Data Index: 692634 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.5123. Min Act: -0.0000

Data Index: 628189 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.3470. Min Act: -0.0000

Data Index: 370606 (C4 (Web Text))

Max Activating Token Index: 643