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

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

Neuron 3202 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8097. Min Range: -3.8097

Max Act: 3.8097. Min Act: -0.0000

Data Index: 45336 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 3.8097. Min Range: -3.8097

Max Act: 3.4073. Min Act: -0.0000

Data Index: 114026 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 3.8097. Min Range: -3.8097

Max Act: 2.8590. Min Act: -0.0000

Data Index: 111806 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 3.8097. Min Range: -3.8097

Max Act: 3.0990. Min Act: -0.0001

Data Index: 1362313 (Python Code)

Max Activating Token Index: 613

Text #4

Max Range: 3.8097. Min Range: -3.8097

Max Act: 2.6495. Min Act: -0.0000

Data Index: 1256457 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 3.8097. Min Range: -3.8097

Max Act: 2.3922. Min Act: -0.0000

Data Index: 483888 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 3.8097. Min Range: -3.8097

Max Act: 2.3659. Min Act: -0.0000

Data Index: 399307 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 3.8097. Min Range: -3.8097

Max Act: 2.3398. Min Act: -0.0000

Data Index: 178894 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 3.8097. Min Range: -3.8097

Max Act: 2.2741. Min Act: -0.0000

Data Index: 1312644 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 3.8097. Min Range: -3.8097

Max Act: 2.1249. Min Act: -0.0000

Data Index: 1308384 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 3.8097. Min Range: -3.8097

Max Act: 1.9529. Min Act: -0.0000

Data Index: 1101180 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 3.8097. Min Range: -3.8097

Max Act: 1.8215. Min Act: -0.0000

Data Index: 579748 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 3.8097. Min Range: -3.8097

Max Act: 1.9130. Min Act: -0.0000

Data Index: 925131 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 3.8097. Min Range: -3.8097

Max Act: 2.0090. Min Act: -0.0000

Data Index: 577602 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 3.8097. Min Range: -3.8097

Max Act: 1.9455. Min Act: -0.0000

Data Index: 159275 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 3.8097. Min Range: -3.8097

Max Act: 1.9199. Min Act: -0.0000

Data Index: 806089 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 3.8097. Min Range: -3.8097

Max Act: 2.0373. Min Act: -0.0000

Data Index: 164064 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 3.8097. Min Range: -3.8097

Max Act: 1.8111. Min Act: -0.0000

Data Index: 383575 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 3.8097. Min Range: -3.8097

Max Act: 1.8851. Min Act: -0.0000

Data Index: 727914 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 3.8097. Min Range: -3.8097

Max Act: 1.6717. Min Act: -0.0000

Data Index: 1308199 (C4 (Web Text))

Max Activating Token Index: 130