Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2583 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.5897. Min Act: -0.0001

Data Index: 834203 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4675. Min Act: -0.0001

Data Index: 33983 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4295. Min Act: -0.0001

Data Index: 457444 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4641. Min Act: -0.0001

Data Index: 1015075 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4502. Min Act: -0.0001

Data Index: 186688 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4609. Min Act: -0.0001

Data Index: 1297150 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4303. Min Act: -0.0001

Data Index: 752720 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3921. Min Act: -0.0001

Data Index: 425915 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3804. Min Act: -0.0001

Data Index: 923765 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4661. Min Act: -0.0001

Data Index: 1174410 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4518. Min Act: -0.0001

Data Index: 1118061 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3737. Min Act: -0.0001

Data Index: 773785 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4035. Min Act: -0.0001

Data Index: 215030 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3805. Min Act: -0.0001

Data Index: 994332 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3877. Min Act: -0.0001

Data Index: 675893 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3631. Min Act: -0.0001

Data Index: 131332 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3953. Min Act: -0.0001

Data Index: 502877 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3817. Min Act: -0.0001

Data Index: 911420 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4000. Min Act: -0.0001

Data Index: 118210 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.3657. Min Act: -0.0001

Data Index: 1535835 (Python Code)

Max Activating Token Index: 108