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

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

Neuron 2525 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.5384. Min Act: -0.0000

Data Index: 199505 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1021263 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4913. Min Act: 0.0000

Data Index: 1228564 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4714. Min Act: -0.0000

Data Index: 993962 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4682. Min Act: -0.0000

Data Index: 544698 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4672. Min Act: -0.0000

Data Index: 700372 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4653. Min Act: -0.0000

Data Index: 996427 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4591. Min Act: -0.0000

Data Index: 109927 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4566. Min Act: 0.0000

Data Index: 382792 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4532. Min Act: -0.0000

Data Index: 331600 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4514. Min Act: -0.0000

Data Index: 564221 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4248. Min Act: -0.0000

Data Index: 660750 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4490. Min Act: -0.0000

Data Index: 506575 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4248. Min Act: -0.0000

Data Index: 342966 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4329. Min Act: -0.0000

Data Index: 393347 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4167. Min Act: -0.0000

Data Index: 331161 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4416. Min Act: 0.0000

Data Index: 1248098 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1188330 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4410. Min Act: -0.0000

Data Index: 818257 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.5384. Min Range: -0.5384

Max Act: 0.4093. Min Act: -0.0000

Data Index: 556202 (C4 (Web Text))

Max Activating Token Index: 970