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

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

Neuron 4424 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2984. Min Act: -0.0000

Data Index: 1063684 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1663. Min Act: -0.0000

Data Index: 906881 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1941. Min Act: -0.0000

Data Index: 582274 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1473. Min Act: -0.0000

Data Index: 38475 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.0466. Min Act: -0.0001

Data Index: 1044673 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.0465. Min Act: -0.0000

Data Index: 1238922 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.9420. Min Act: -0.0000

Data Index: 487594 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.0828. Min Act: -0.0000

Data Index: 199149 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.0651. Min Act: -0.0000

Data Index: 906412 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1029983 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.9895. Min Act: -0.0000

Data Index: 567249 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.0801. Min Act: -0.0000

Data Index: 1282652 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.9873. Min Act: -0.0001

Data Index: 1058439 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1015182 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.0067. Min Act: -0.0000

Data Index: 1090664 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.9970. Min Act: -0.0000

Data Index: 899101 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.9936. Min Act: -0.0000

Data Index: 230815 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.0282. Min Act: -0.0000

Data Index: 1254652 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.9803. Min Act: -0.0000

Data Index: 932846 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.9531. Min Act: -0.0000

Data Index: 291379 (C4 (Web Text))

Max Activating Token Index: 269