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

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

Neuron 550 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0843. Min Act: -0.0003

Data Index: 380176 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0870. Min Act: -0.0003

Data Index: 519913 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0855. Min Act: -0.0003

Data Index: 22341 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0725. Min Act: -0.0003

Data Index: 596791 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0696. Min Act: -0.0003

Data Index: 1130737 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0595. Min Act: -0.0003

Data Index: 133436 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0715. Min Act: -0.0003

Data Index: 76835 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0699. Min Act: -0.0003

Data Index: 1045391 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0671. Min Act: -0.0003

Data Index: 480063 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0665. Min Act: -0.0003

Data Index: 244776 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0660. Min Act: -0.0003

Data Index: 477164 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0710. Min Act: -0.0003

Data Index: 413913 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0682. Min Act: -0.0003

Data Index: 286838 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0659. Min Act: -0.0003

Data Index: 612922 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0633. Min Act: -0.0003

Data Index: 1100065 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1046377 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0630. Min Act: -0.0003

Data Index: 98536 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0626. Min Act: -0.0003

Data Index: 182584 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1345306 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0621. Min Act: -0.0003

Data Index: 760298 (C4 (Web Text))

Max Activating Token Index: 599