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

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

Neuron 5640 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2620. Min Range: -5.2620

Max Act: 5.2620. Min Act: -0.0000

Data Index: 251524 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 5.2620. Min Range: -5.2620

Max Act: 4.7172. Min Act: -0.0000

Data Index: 868248 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 5.2620. Min Range: -5.2620

Max Act: 3.9033. Min Act: -0.0000

Data Index: 739725 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 5.2620. Min Range: -5.2620

Max Act: 4.0364. Min Act: -0.0000

Data Index: 1024768 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 5.2620. Min Range: -5.2620

Max Act: 4.1415. Min Act: -0.0000

Data Index: 427223 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 5.2620. Min Range: -5.2620

Max Act: 3.7537. Min Act: -0.0000

Data Index: 426842 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 5.2620. Min Range: -5.2620

Max Act: 3.5304. Min Act: -0.0000

Data Index: 1321126 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 5.2620. Min Range: -5.2620

Max Act: 3.8563. Min Act: -0.0000

Data Index: 880517 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 5.2620. Min Range: -5.2620

Max Act: 3.4827. Min Act: -0.0000

Data Index: 783514 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 5.2620. Min Range: -5.2620

Max Act: 3.9010. Min Act: -0.0000

Data Index: 164599 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 5.2620. Min Range: -5.2620

Max Act: 2.8968. Min Act: -0.0000

Data Index: 85700 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 5.2620. Min Range: -5.2620

Max Act: 3.0328. Min Act: -0.0000

Data Index: 315654 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 5.2620. Min Range: -5.2620

Max Act: 3.0801. Min Act: -0.0000

Data Index: 272550 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 5.2620. Min Range: -5.2620

Max Act: 2.9337. Min Act: -0.0000

Data Index: 660573 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 5.2620. Min Range: -5.2620

Max Act: 3.1427. Min Act: -0.0000

Data Index: 323452 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 5.2620. Min Range: -5.2620

Max Act: 3.2286. Min Act: -0.0000

Data Index: 245520 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 5.2620. Min Range: -5.2620

Max Act: 2.9224. Min Act: -0.0000

Data Index: 1315643 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 5.2620. Min Range: -5.2620

Max Act: 2.7065. Min Act: -0.0000

Data Index: 59869 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 5.2620. Min Range: -5.2620

Max Act: 2.9892. Min Act: -0.0000

Data Index: 1042075 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 5.2620. Min Range: -5.2620

Max Act: 2.8134. Min Act: -0.0000

Data Index: 582028 (C4 (Web Text))

Max Activating Token Index: 715