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

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

Neuron 2166 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: 4.3423. Min Range: -4.3423

Max Act: 4.1693. Min Act: -0.0000

Data Index: 618302 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.3423. Min Act: -0.0000

Data Index: 362574 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.3013. Min Act: -0.0000

Data Index: 865504 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.9938. Min Act: -0.0000

Data Index: 13445 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.7796. Min Act: -0.0000

Data Index: 259723 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.2631. Min Act: -0.0000

Data Index: 1132765 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.9150. Min Act: -0.0000

Data Index: 404836 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.9838. Min Act: -0.0000

Data Index: 419838 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.9375. Min Act: -0.0000

Data Index: 1197104 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.8585. Min Act: -0.0000

Data Index: 126066 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.8045. Min Act: -0.0000

Data Index: 758718 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.7906. Min Act: -0.0000

Data Index: 1289290 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.6244. Min Act: -0.0000

Data Index: 1056996 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.5942. Min Act: -0.0000

Data Index: 1465151 (Python Code)

Max Activating Token Index: 938

Text #14

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.9130. Min Act: -0.0000

Data Index: 1598794 (Python Code)

Max Activating Token Index: 942

Text #15

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.5910. Min Act: -0.0000

Data Index: 280440 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.7550. Min Act: -0.0000

Data Index: 1462815 (Python Code)

Max Activating Token Index: 728

Text #17

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.5950. Min Act: -0.0000

Data Index: 1154889 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.5746. Min Act: -0.0000

Data Index: 1106758 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.4130. Min Act: -0.0000

Data Index: 1482617 (Python Code)

Max Activating Token Index: 940