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

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

Neuron 826 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0839. Min Act: -0.0006

Data Index: 227757 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0797. Min Act: -0.0006

Data Index: 1102674 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0773. Min Act: -0.0006

Data Index: 1252123 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0922. Min Act: -0.0006

Data Index: 1224909 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0784. Min Act: -0.0006

Data Index: 233122 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0687. Min Act: -0.0006

Data Index: 1223822 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0655. Min Act: -0.0006

Data Index: 200034 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0750. Min Act: -0.0006

Data Index: 919954 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0692. Min Act: -0.0006

Data Index: 658581 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0618. Min Act: -0.0006

Data Index: 164919 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0638. Min Act: -0.0006

Data Index: 894478 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0596. Min Act: -0.0006

Data Index: 188315 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0693. Min Act: -0.0006

Data Index: 887381 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0696. Min Act: -0.0006

Data Index: 223357 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0608. Min Act: -0.0006

Data Index: 761167 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0592. Min Act: -0.0006

Data Index: 243884 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0736. Min Act: -0.0006

Data Index: 1032332 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0691. Min Act: -0.0006

Data Index: 1279586 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0587. Min Act: -0.0006

Data Index: 661963 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0680. Min Act: -0.0006

Data Index: 908127 (C4 (Web Text))

Max Activating Token Index: 878