Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1018 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.4502. Min Act: -0.0001

Data Index: 1331245 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.3862. Min Act: -0.0000

Data Index: 644696 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.3544. Min Act: -0.0001

Data Index: 441558 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.2701. Min Act: -0.0000

Data Index: 1041542 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.2583. Min Act: -0.0001

Data Index: 811959 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.2348. Min Act: -0.0001

Data Index: 517728 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.2433. Min Act: -0.0001

Data Index: 235676 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.1664. Min Act: -0.0001

Data Index: 1260684 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.0798. Min Act: -0.0001

Data Index: 513162 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.1822. Min Act: -0.0000

Data Index: 1082203 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.0815. Min Act: -0.0001

Data Index: 1331684 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.0139. Min Act: -0.0000

Data Index: 800647 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 2.4502. Min Range: -2.4502

Max Act: 1.9798. Min Act: -0.0001

Data Index: 1294079 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 2.4502. Min Range: -2.4502

Max Act: 1.9782. Min Act: -0.0001

Data Index: 920633 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.0388. Min Act: -0.0001

Data Index: 50983 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.0562. Min Act: -0.0000

Data Index: 166954 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.0116. Min Act: -0.0001

Data Index: 887171 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 2.4502. Min Range: -2.4502

Max Act: 2.0353. Min Act: -0.0000

Data Index: 68950 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 2.4502. Min Range: -2.4502

Max Act: 1.9760. Min Act: -0.0000

Data Index: 1002395 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 2.4502. Min Range: -2.4502

Max Act: 1.9197. Min Act: -0.0001

Data Index: 643003 (C4 (Web Text))

Max Activating Token Index: 5