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

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

Neuron 3515 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0020. Min Range: -1.0020

Max Act: 1.0020. Min Act: -0.0001

Data Index: 474130 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.8789. Min Act: -0.0001

Data Index: 1294137 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.9534. Min Act: -0.0001

Data Index: 980632 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.9754. Min Act: -0.0001

Data Index: 949359 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.9620. Min Act: -0.0001

Data Index: 670902 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.9508. Min Act: -0.0001

Data Index: 296611 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.8760. Min Act: -0.0001

Data Index: 1224893 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.9121. Min Act: -0.0001

Data Index: 944518 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.8438. Min Act: -0.0001

Data Index: 334977 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.9476. Min Act: -0.0001

Data Index: 1170787 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.8943. Min Act: -0.0001

Data Index: 636363 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.8753. Min Act: -0.0001

Data Index: 945659 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.8289. Min Act: -0.0001

Data Index: 924647 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.8805. Min Act: -0.0001

Data Index: 1343380 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.8588. Min Act: -0.0001

Data Index: 21772 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.7661. Min Act: -0.0001

Data Index: 1191165 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.8571. Min Act: -0.0001

Data Index: 1255583 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.7857. Min Act: -0.0001

Data Index: 21182 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.8524. Min Act: -0.0001

Data Index: 522415 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 1.0020. Min Range: -1.0020

Max Act: 0.7971. Min Act: -0.0001

Data Index: 913881 (C4 (Web Text))

Max Activating Token Index: 703