Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3346 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.4631. Min Act: -0.0000

Data Index: 204381 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.1854. Min Act: -0.0000

Data Index: 650656 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.3800. Min Act: -0.0000

Data Index: 1315008 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.3524. Min Act: -0.0000

Data Index: 1322912 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.1698. Min Act: -0.0000

Data Index: 555771 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.2466. Min Act: -0.0000

Data Index: 249253 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.1393. Min Act: -0.0000

Data Index: 229006 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.2229. Min Act: -0.0000

Data Index: 338687 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.1968. Min Act: -0.0000

Data Index: 595609 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.1848. Min Act: -0.0000

Data Index: 126963 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.1814. Min Act: -0.0000

Data Index: 79954 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.2636. Min Act: -0.0000

Data Index: 278518 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.1242. Min Act: -0.0000

Data Index: 1146086 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.1133. Min Act: -0.0000

Data Index: 610090 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 2.4631. Min Range: -2.4631

Max Act: 1.9813. Min Act: -0.0000

Data Index: 504512 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.2228. Min Act: -0.0000

Data Index: 1068824 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.1035. Min Act: -0.0000

Data Index: 193891 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 2.4631. Min Range: -2.4631

Max Act: 2.0970. Min Act: -0.0000

Data Index: 82643 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 2.4631. Min Range: -2.4631

Max Act: 1.9792. Min Act: -0.0000

Data Index: 256087 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 2.4631. Min Range: -2.4631

Max Act: 1.9590. Min Act: -0.0000

Data Index: 171259 (C4 (Web Text))

Max Activating Token Index: 673