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

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

Neuron 3006 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.6911. Min Act: -0.0000

Data Index: 817929 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.5451. Min Act: -0.0000

Data Index: 789537 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.4294. Min Act: -0.0000

Data Index: 117803 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.4159. Min Act: -0.0000

Data Index: 555119 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.4540. Min Act: -0.0000

Data Index: 828366 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3407. Min Act: -0.0000

Data Index: 377037 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3282. Min Act: -0.0000

Data Index: 374815 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3410. Min Act: -0.0000

Data Index: 1026969 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.2962. Min Act: -0.0000

Data Index: 11477 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.2756. Min Act: -0.0000

Data Index: 1188229 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3392. Min Act: -0.0000

Data Index: 497907 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.2509. Min Act: -0.0000

Data Index: 1348711 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.2830. Min Act: -0.0000

Data Index: 115001 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.1955. Min Act: -0.0000

Data Index: 273985 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.2528. Min Act: -0.0000

Data Index: 243567 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.2151. Min Act: -0.0000

Data Index: 570982 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.2836. Min Act: -0.0000

Data Index: 693016 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.1967. Min Act: -0.0000

Data Index: 952063 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.2719. Min Act: -0.0000

Data Index: 531425 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.1661. Min Act: -0.0000

Data Index: 266236 (C4 (Web Text))

Max Activating Token Index: 787