Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1719 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0024. Min Act: -0.0006

Data Index: 1202535 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0022. Min Act: -0.0006

Data Index: 1322676 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0022. Min Act: -0.0006

Data Index: 836501 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0006

Data Index: 1188886 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0022. Min Act: -0.0006

Data Index: 1134909 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0006

Data Index: 356200 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0006

Data Index: 922279 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0006

Data Index: 1263710 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0006

Data Index: 115988 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0020. Min Act: -0.0006

Data Index: 391356 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0006

Data Index: 918701 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0006

Data Index: 961297 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0020. Min Act: -0.0006

Data Index: 311315 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0020. Min Act: -0.0006

Data Index: 1614790 (Python Code)

Max Activating Token Index: 529

Text #14

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0020. Min Act: -0.0006

Data Index: 1546074 (Python Code)

Max Activating Token Index: 533

Text #15

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0006

Data Index: 1295775 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0020. Min Act: -0.0006

Data Index: 1441942 (Python Code)

Max Activating Token Index: 545

Text #17

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0020. Min Act: -0.0006

Data Index: 1114852 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0020. Min Act: -0.0006

Data Index: 1453886 (Python Code)

Max Activating Token Index: 537

Text #19

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0020. Min Act: -0.0006

Data Index: 101007 (C4 (Web Text))

Max Activating Token Index: 480