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

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

Neuron 3542 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2779. Min Range: -2.2779

Max Act: 2.2016. Min Act: -0.0000

Data Index: 567937 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 2.2779. Min Range: -2.2779

Max Act: 2.2779. Min Act: -0.0000

Data Index: 878736 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 2.2779. Min Range: -2.2779

Max Act: 2.2669. Min Act: -0.0000

Data Index: 313479 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 2.2779. Min Range: -2.2779

Max Act: 2.2106. Min Act: -0.0000

Data Index: 231354 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 2.2779. Min Range: -2.2779

Max Act: 2.0500. Min Act: -0.0000

Data Index: 1120005 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 2.2779. Min Range: -2.2779

Max Act: 2.1355. Min Act: -0.0000

Data Index: 156107 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.8291. Min Act: -0.0000

Data Index: 1484395 (Python Code)

Max Activating Token Index: 552

Text #7

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.9184. Min Act: -0.0000

Data Index: 936199 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.9173. Min Act: -0.0000

Data Index: 655517 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.8918. Min Act: -0.0000

Data Index: 269194 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.8822. Min Act: -0.0000

Data Index: 1034574 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.8503. Min Act: -0.0000

Data Index: 689875 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.7378. Min Act: -0.0000

Data Index: 139764 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.7588. Min Act: -0.0000

Data Index: 1617327 (Python Code)

Max Activating Token Index: 671

Text #14

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.8127. Min Act: -0.0000

Data Index: 843589 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.8096. Min Act: -0.0000

Data Index: 1262830 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.8097. Min Act: -0.0000

Data Index: 622201 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.7893. Min Act: -0.0000

Data Index: 968457 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.6488. Min Act: -0.0000

Data Index: 786570 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.6379. Min Act: -0.0000

Data Index: 229594 (C4 (Web Text))

Max Activating Token Index: 493