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

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

Neuron 1709 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0897. Min Act: -0.0004

Data Index: 498666 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0891. Min Act: -0.0004

Data Index: 1084479 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0765. Min Act: -0.0004

Data Index: 1175597 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0785. Min Act: -0.0004

Data Index: 577651 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0795. Min Act: -0.0004

Data Index: 1353638 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0831. Min Act: -0.0004

Data Index: 556465 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0814. Min Act: -0.0004

Data Index: 882764 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0847. Min Act: -0.0004

Data Index: 859454 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0885. Min Act: -0.0004

Data Index: 80487 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0846. Min Act: -0.0004

Data Index: 734310 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0810. Min Act: -0.0004

Data Index: 888213 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0833. Min Act: -0.0004

Data Index: 493216 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0613. Min Act: -0.0004

Data Index: 627029 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0898. Min Act: -0.0004

Data Index: 871817 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0702. Min Act: -0.0004

Data Index: 470622 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0759. Min Act: -0.0004

Data Index: 127751 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0701. Min Act: -0.0004

Data Index: 303174 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0753. Min Act: -0.0004

Data Index: 1087984 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0818. Min Act: -0.0004

Data Index: 192750 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0712. Min Act: -0.0004

Data Index: 518315 (C4 (Web Text))

Max Activating Token Index: 686