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

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

Neuron 1223 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: 0.1090. Min Range: -0.1090

Max Act: 0.1088. Min Act: -0.0001

Data Index: 87320 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1001. Min Act: -0.0001

Data Index: 858012 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1090. Min Act: -0.0001

Data Index: 222936 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1014. Min Act: -0.0001

Data Index: 744773 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1462782 (Python Code)

Max Activating Token Index: 1010

Text #5

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1028. Min Act: -0.0001

Data Index: 389243 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1569163 (Python Code)

Max Activating Token Index: 956

Text #7

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1390369 (Python Code)

Max Activating Token Index: 662

Text #8

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0983. Min Act: -0.0001

Data Index: 402363 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0975. Min Act: -0.0001

Data Index: 308847 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0971. Min Act: -0.0001

Data Index: 210167 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1000. Min Act: -0.0001

Data Index: 216661 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1602007 (Python Code)

Max Activating Token Index: 942

Text #13

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1490213 (Python Code)

Max Activating Token Index: 1017

Text #14

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1535911 (Python Code)

Max Activating Token Index: 856

Text #15

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0978. Min Act: -0.0001

Data Index: 124386 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0975. Min Act: -0.0001

Data Index: 11922 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1249533 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1431627 (Python Code)

Max Activating Token Index: 135

Text #19

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1416626 (Python Code)

Max Activating Token Index: 367