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

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

Neuron 732 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1016. Min Range: -1.1016

Max Act: 1.1016. Min Act: -0.0000

Data Index: 854773 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 1.1016. Min Range: -1.1016

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1087579 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.9517. Min Act: -0.0000

Data Index: 830228 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8871. Min Act: -0.0000

Data Index: 1194224 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8864. Min Act: -0.0000

Data Index: 837282 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.9182. Min Act: -0.0000

Data Index: 67915 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8095. Min Act: -0.0000

Data Index: 362995 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8525. Min Act: -0.0000

Data Index: 861287 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1143847 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1462026 (Python Code)

Max Activating Token Index: 343

Text #10

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8561. Min Act: -0.0000

Data Index: 624511 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8591. Min Act: -0.0000

Data Index: 527487 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8262. Min Act: -0.0000

Data Index: 531168 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1025123 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7695. Min Act: -0.0000

Data Index: 576364 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7979. Min Act: -0.0000

Data Index: 263540 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8007. Min Act: -0.0000

Data Index: 818073 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1111681 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7940. Min Act: -0.0000

Data Index: 806192 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7968. Min Act: -0.0000

Data Index: 1355055 (C4 (Web Text))

Max Activating Token Index: 336