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

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

Neuron 4891 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0698. Min Range: -4.0698

Max Act: 3.6364. Min Act: -0.0000

Data Index: 148184 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 4.0698. Min Range: -4.0698

Max Act: 4.0698. Min Act: -0.0000

Data Index: 1308464 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 4.0698. Min Range: -4.0698

Max Act: 3.7461. Min Act: -0.0001

Data Index: 55029 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 4.0698. Min Range: -4.0698

Max Act: 3.5434. Min Act: -0.0001

Data Index: 141485 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 4.0698. Min Range: -4.0698

Max Act: 3.6392. Min Act: -0.0000

Data Index: 266482 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 4.0698. Min Range: -4.0698

Max Act: 3.4259. Min Act: -0.0000

Data Index: 819940 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 4.0698. Min Range: -4.0698

Max Act: 2.9609. Min Act: -0.0000

Data Index: 916844 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 4.0698. Min Range: -4.0698

Max Act: 2.8960. Min Act: -0.0000

Data Index: 533212 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 4.0698. Min Range: -4.0698

Max Act: 2.9528. Min Act: -0.0000

Data Index: 505463 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 4.0698. Min Range: -4.0698

Max Act: 2.8135. Min Act: -0.0000

Data Index: 213204 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 4.0698. Min Range: -4.0698

Max Act: 2.7734. Min Act: -0.0000

Data Index: 574921 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 4.0698. Min Range: -4.0698

Max Act: 2.5800. Min Act: -0.0000

Data Index: 648863 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 4.0698. Min Range: -4.0698

Max Act: 2.6783. Min Act: -0.0000

Data Index: 421026 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 4.0698. Min Range: -4.0698

Max Act: 2.5361. Min Act: -0.0000

Data Index: 855564 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 4.0698. Min Range: -4.0698

Max Act: 2.3156. Min Act: -0.0000

Data Index: 1168875 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 4.0698. Min Range: -4.0698

Max Act: 2.1584. Min Act: -0.0000

Data Index: 1181329 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 4.0698. Min Range: -4.0698

Max Act: 2.2458. Min Act: -0.0000

Data Index: 154638 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 4.0698. Min Range: -4.0698

Max Act: 2.0919. Min Act: -0.0000

Data Index: 688307 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 4.0698. Min Range: -4.0698

Max Act: 1.8933. Min Act: -0.0000

Data Index: 280836 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 4.0698. Min Range: -4.0698

Max Act: 1.9721. Min Act: -0.0000

Data Index: 1113980 (C4 (Web Text))

Max Activating Token Index: 478