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

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

Neuron 3310 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1014693 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.9073. Min Act: -0.0000

Data Index: 755787 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.9311. Min Act: -0.0000

Data Index: 983092 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.8585. Min Act: -0.0000

Data Index: 817782 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.8802. Min Act: -0.0000

Data Index: 752399 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.8667. Min Act: -0.0000

Data Index: 401137 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7946. Min Act: -0.0000

Data Index: 308009 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1083683 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7597. Min Act: -0.0000

Data Index: 1230614 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7395. Min Act: -0.0000

Data Index: 291615 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1079439 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1043282 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1332378 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7118. Min Act: -0.0000

Data Index: 534768 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7830. Min Act: -0.0000

Data Index: 286333 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7248. Min Act: -0.0000

Data Index: 997005 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7234. Min Act: -0.0000

Data Index: 14170 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7420. Min Act: -0.0000

Data Index: 251051 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1174265 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1265586 (C4 (Web Text))

Max Activating Token Index: 857