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

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

Neuron 391 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4750. Min Range: -5.4750

Max Act: 5.4750. Min Act: -0.0000

Data Index: 117087 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.9179. Min Act: -0.0000

Data Index: 1354521 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 5.4750. Min Range: -5.4750

Max Act: 4.0306. Min Act: -0.0000

Data Index: 757064 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 5.4750. Min Range: -5.4750

Max Act: 4.0307. Min Act: -0.0000

Data Index: 812605 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 5.4750. Min Range: -5.4750

Max Act: 4.0139. Min Act: -0.0000

Data Index: 859290 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.8551. Min Act: -0.0000

Data Index: 173323 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.7516. Min Act: -0.0000

Data Index: 641615 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.6935. Min Act: -0.0000

Data Index: 201080 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.7761. Min Act: -0.0000

Data Index: 297484 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.5642. Min Act: -0.0000

Data Index: 853281 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.6237. Min Act: -0.0000

Data Index: 117549 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.3945. Min Act: -0.0000

Data Index: 1250956 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.6974. Min Act: -0.0000

Data Index: 1268830 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.3865. Min Act: -0.0000

Data Index: 878640 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.2106. Min Act: -0.0000

Data Index: 1141108 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.3334. Min Act: -0.0000

Data Index: 858870 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.1813. Min Act: -0.0000

Data Index: 252351 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.2482. Min Act: -0.0000

Data Index: 812011 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.4073. Min Act: -0.0000

Data Index: 733373 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 5.4750. Min Range: -5.4750

Max Act: 3.0680. Min Act: -0.0000

Data Index: 963442 (C4 (Web Text))

Max Activating Token Index: 281