Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1035 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0755. Min Act: -0.0002

Data Index: 26979 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0002

Data Index: 439460 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0754. Min Act: -0.0002

Data Index: 304715 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1322515 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0715. Min Act: -0.0002

Data Index: 354021 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0711. Min Act: -0.0002

Data Index: 590592 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0719. Min Act: -0.0002

Data Index: 264343 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0729. Min Act: -0.0002

Data Index: 466065 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0688. Min Act: -0.0002

Data Index: 533951 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0691. Min Act: -0.0002

Data Index: 501813 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0688. Min Act: -0.0002

Data Index: 730185 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1283968 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1285132 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0700. Min Act: -0.0001

Data Index: 554320 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0661. Min Act: -0.0002

Data Index: 531552 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0671. Min Act: -0.0002

Data Index: 71988 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0641. Min Act: -0.0002

Data Index: 764107 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1315733 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0667. Min Act: -0.0001

Data Index: 265687 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0643. Min Act: -0.0002

Data Index: 770855 (C4 (Web Text))

Max Activating Token Index: 134