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

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

Neuron 5638 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9562. Min Range: -5.9562

Max Act: 5.9562. Min Act: -0.0000

Data Index: 167269 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 5.9562. Min Range: -5.9562

Max Act: 5.6092. Min Act: -0.0000

Data Index: 928916 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 5.9562. Min Range: -5.9562

Max Act: 5.0239. Min Act: -0.0001

Data Index: 525510 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 5.9562. Min Range: -5.9562

Max Act: 5.0135. Min Act: -0.0001

Data Index: 604889 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 5.9562. Min Range: -5.9562

Max Act: 5.0004. Min Act: -0.0001

Data Index: 1000132 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.6566. Min Act: -0.0000

Data Index: 1117786 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.9316. Min Act: -0.0000

Data Index: 469988 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.4070. Min Act: -0.0001

Data Index: 1043152 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.5113. Min Act: -0.0001

Data Index: 979537 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.4499. Min Act: -0.0000

Data Index: 1160286 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.1134. Min Act: -0.0001

Data Index: 687383 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.2350. Min Act: -0.0001

Data Index: 269133 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.4009. Min Act: -0.0001

Data Index: 1037054 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.0529. Min Act: -0.0001

Data Index: 1277145 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.0702. Min Act: -0.0000

Data Index: 900843 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.2144. Min Act: -0.0001

Data Index: 352294 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.3685. Min Act: -0.0000

Data Index: 19155 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 5.9562. Min Range: -5.9562

Max Act: 3.8873. Min Act: -0.0000

Data Index: 1131698 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 5.9562. Min Range: -5.9562

Max Act: 4.1282. Min Act: -0.0001

Data Index: 526699 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 5.9562. Min Range: -5.9562

Max Act: 3.9573. Min Act: -0.0001

Data Index: 979845 (C4 (Web Text))

Max Activating Token Index: 496