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

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

Neuron 5069 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1048. Min Range: -1.1048

Max Act: 1.0484. Min Act: -0.0000

Data Index: 795469 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 1.1048. Min Range: -1.1048

Max Act: 1.1048. Min Act: -0.0000

Data Index: 75753 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.8916. Min Act: -0.0000

Data Index: 715917 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.8817. Min Act: -0.0000

Data Index: 286351 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.7392. Min Act: -0.0000

Data Index: 357113 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1029313 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.7423. Min Act: -0.0000

Data Index: 356171 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.6962. Min Act: -0.0000

Data Index: 484603 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.7064. Min Act: -0.0000

Data Index: 896220 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1049761 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.6887. Min Act: -0.0000

Data Index: 479907 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1306098 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1202627 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.6944. Min Act: -0.0000

Data Index: 878775 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.6245. Min Act: -0.0000

Data Index: 489905 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.6548. Min Act: -0.0000

Data Index: 573824 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.6394. Min Act: -0.0000

Data Index: 325001 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.6400. Min Act: -0.0000

Data Index: 871260 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.6365. Min Act: -0.0000

Data Index: 51545 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.6311. Min Act: -0.0000

Data Index: 380294 (C4 (Web Text))

Max Activating Token Index: 797