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

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

Neuron 1375 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: 0.7984. Min Range: -0.7984

Max Act: 0.7984. Min Act: -0.0000

Data Index: 342233 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6248. Min Act: -0.0000

Data Index: 899583 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1007864 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1002397 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6077. Min Act: -0.0000

Data Index: 530513 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5832. Min Act: -0.0000

Data Index: 69406 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5768. Min Act: -0.0000

Data Index: 6014 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5462. Min Act: -0.0000

Data Index: 107319 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5705. Min Act: -0.0000

Data Index: 989883 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5489. Min Act: -0.0000

Data Index: 731969 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1062482 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5576. Min Act: -0.0000

Data Index: 392076 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5544. Min Act: -0.0000

Data Index: 760553 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5568. Min Act: -0.0000

Data Index: 33870 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5676. Min Act: -0.0000

Data Index: 355511 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5396. Min Act: -0.0000

Data Index: 363374 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5512. Min Act: -0.0000

Data Index: 891383 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5350. Min Act: -0.0000

Data Index: 556071 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5263. Min Act: -0.0000

Data Index: 265307 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1233258 (C4 (Web Text))

Max Activating Token Index: 384