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

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

Neuron 4389 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.9641. Min Act: -0.0000

Data Index: 508722 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7813. Min Act: -0.0000

Data Index: 457976 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1194202 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7682. Min Act: -0.0000

Data Index: 12792 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7604. Min Act: -0.0000

Data Index: 750547 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7636. Min Act: -0.0000

Data Index: 745891 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7593. Min Act: -0.0000

Data Index: 957992 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6424. Min Act: -0.0000

Data Index: 775925 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7645. Min Act: -0.0000

Data Index: 270570 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7177. Min Act: -0.0000

Data Index: 755090 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1226644 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7178. Min Act: -0.0000

Data Index: 822888 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6768. Min Act: -0.0000

Data Index: 621279 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6294. Min Act: -0.0000

Data Index: 739564 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1189470 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1002355 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6627. Min Act: -0.0000

Data Index: 659557 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6608. Min Act: -0.0000

Data Index: 945912 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7058. Min Act: -0.0000

Data Index: 739920 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.6402. Min Act: -0.0000

Data Index: 794907 (C4 (Web Text))

Max Activating Token Index: 255