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

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

Neuron 202 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2391. Min Act: -0.0001

Data Index: 1562892 (Python Code)

Max Activating Token Index: 629

Text #1

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2319. Min Act: -0.0001

Data Index: 1578549 (Python Code)

Max Activating Token Index: 901

Text #2

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2021. Min Act: -0.0001

Data Index: 306690 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2103. Min Act: -0.0001

Data Index: 529728 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1990. Min Act: -0.0001

Data Index: 488640 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1861. Min Act: -0.0001

Data Index: 975339 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2033. Min Act: -0.0001

Data Index: 1065070 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2097. Min Act: -0.0001

Data Index: 1511996 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1906. Min Act: -0.0001

Data Index: 72910 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1999. Min Act: -0.0001

Data Index: 901817 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1915. Min Act: -0.0001

Data Index: 1577933 (Python Code)

Max Activating Token Index: 102

Text #11

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1868. Min Act: -0.0001

Data Index: 1465107 (Python Code)

Max Activating Token Index: 113

Text #12

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2094. Min Act: -0.0001

Data Index: 1534144 (Python Code)

Max Activating Token Index: 835

Text #13

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1953. Min Act: -0.0001

Data Index: 1118449 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1638925 (Python Code)

Max Activating Token Index: 826

Text #15

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1968. Min Act: -0.0001

Data Index: 690630 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1874. Min Act: -0.0001

Data Index: 1136246 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1853. Min Act: -0.0001

Data Index: 909796 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1963. Min Act: -0.0001

Data Index: 1635150 (Python Code)

Max Activating Token Index: 410

Text #19

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1797. Min Act: -0.0001

Data Index: 1453278 (Python Code)

Max Activating Token Index: 329