Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2957 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.4313. Min Act: -0.0001

Data Index: 124641 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.4057. Min Act: -0.0001

Data Index: 512857 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.4069. Min Act: -0.0001

Data Index: 600313 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3789. Min Act: -0.0001

Data Index: 632257 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3953. Min Act: -0.0001

Data Index: 110900 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3923. Min Act: -0.0001

Data Index: 378177 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3840. Min Act: -0.0001

Data Index: 1227182 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3830. Min Act: -0.0001

Data Index: 492372 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3908. Min Act: -0.0001

Data Index: 937235 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3785. Min Act: -0.0001

Data Index: 971219 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3736. Min Act: -0.0001

Data Index: 1037113 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3713. Min Act: -0.0001

Data Index: 743335 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3723. Min Act: -0.0001

Data Index: 619407 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3717. Min Act: -0.0001

Data Index: 468632 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3587. Min Act: -0.0001

Data Index: 1103480 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3718. Min Act: -0.0001

Data Index: 72448 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3682. Min Act: -0.0001

Data Index: 934436 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3671. Min Act: -0.0001

Data Index: 1301049 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3653. Min Act: -0.0001

Data Index: 421090 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3772. Min Act: -0.0001

Data Index: 409213 (C4 (Web Text))

Max Activating Token Index: 518