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

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

Neuron 1151 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.4860. Min Act: -0.0000

Data Index: 964320 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.3281. Min Act: -0.0000

Data Index: 334992 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.2950. Min Act: -0.0000

Data Index: 844833 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.2119. Min Act: -0.0000

Data Index: 783927 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1923. Min Act: -0.0000

Data Index: 987721 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.0914. Min Act: -0.0000

Data Index: 825398 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1628. Min Act: -0.0000

Data Index: 1224346 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1193. Min Act: -0.0000

Data Index: 1094105 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.0508. Min Act: -0.0000

Data Index: 337225 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1694. Min Act: 0.0000

Data Index: 430020 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.0844. Min Act: -0.0000

Data Index: 931636 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.0632. Min Act: -0.0000

Data Index: 1044652 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.0184. Min Act: -0.0000

Data Index: 611735 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 1.4860. Min Range: -1.4860

Max Act: 0.9125. Min Act: -0.0000

Data Index: 490626 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 1.4860. Min Range: -1.4860

Max Act: 0.9838. Min Act: -0.0000

Data Index: 296742 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 1.4860. Min Range: -1.4860

Max Act: 0.9691. Min Act: -0.0000

Data Index: 915797 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 1.4860. Min Range: -1.4860

Max Act: 0.9775. Min Act: -0.0000

Data Index: 378474 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.0021. Min Act: -0.0000

Data Index: 671992 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 1.4860. Min Range: -1.4860

Max Act: 0.8755. Min Act: -0.0000

Data Index: 448487 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.4860. Min Range: -1.4860

Max Act: 0.8498. Min Act: -0.0000

Data Index: 926627 (C4 (Web Text))

Max Activating Token Index: 483