Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 914 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0894. Min Act: -0.0001

Data Index: 291554 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0980. Min Act: -0.0001

Data Index: 97183 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0952. Min Act: -0.0001

Data Index: 13741 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1143474 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0942. Min Act: -0.0001

Data Index: 255749 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0890. Min Act: -0.0001

Data Index: 468365 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0826. Min Act: -0.0001

Data Index: 471796 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0798. Min Act: -0.0001

Data Index: 820860 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0811. Min Act: -0.0001

Data Index: 835334 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0840. Min Act: -0.0001

Data Index: 972257 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0779. Min Act: -0.0001

Data Index: 564650 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0773. Min Act: -0.0001

Data Index: 492357 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0796. Min Act: -0.0001

Data Index: 278489 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0797. Min Act: -0.0001

Data Index: 712117 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1006222 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0788. Min Act: -0.0001

Data Index: 566814 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0736. Min Act: -0.0001

Data Index: 59476 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1264290 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1350725 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0814. Min Act: -0.0001

Data Index: 1105641 (C4 (Web Text))

Max Activating Token Index: 586