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

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

Neuron 627 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: 1.9929. Min Range: -1.9929

Max Act: 1.9929. Min Act: -0.0000

Data Index: 924999 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.7938. Min Act: -0.0000

Data Index: 975174 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.8863. Min Act: -0.0000

Data Index: 542272 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.8413. Min Act: -0.0000

Data Index: 1059466 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.7141. Min Act: -0.0000

Data Index: 178487 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.8270. Min Act: -0.0000

Data Index: 881452 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.8192. Min Act: -0.0000

Data Index: 2751 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.7830. Min Act: -0.0000

Data Index: 723383 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.7461. Min Act: -0.0000

Data Index: 1129467 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.7473. Min Act: -0.0000

Data Index: 1227088 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.7449. Min Act: -0.0000

Data Index: 277411 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.7350. Min Act: -0.0000

Data Index: 1048598 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.7540. Min Act: -0.0000

Data Index: 868649 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.7430. Min Act: -0.0000

Data Index: 489379 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.7245. Min Act: -0.0000

Data Index: 312700 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.6094. Min Act: -0.0000

Data Index: 234707 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.7164. Min Act: -0.0000

Data Index: 697751 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.7478. Min Act: -0.0000

Data Index: 947068 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.7067. Min Act: -0.0000

Data Index: 1296750 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 1.9929. Min Range: -1.9929

Max Act: 1.5866. Min Act: -0.0000

Data Index: 223625 (C4 (Web Text))

Max Activating Token Index: 289