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

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

Neuron 2877 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0561. Min Act: -0.0003

Data Index: 817763 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1114504 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0564. Min Act: -0.0003

Data Index: 480110 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0588. Min Act: -0.0003

Data Index: 963651 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0587. Min Act: -0.0003

Data Index: 918462 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0496. Min Act: -0.0003

Data Index: 480850 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0532. Min Act: -0.0003

Data Index: 483439 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0555. Min Act: -0.0003

Data Index: 437480 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0549. Min Act: -0.0003

Data Index: 626934 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0546. Min Act: -0.0003

Data Index: 974834 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0540. Min Act: -0.0003

Data Index: 64058 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0533. Min Act: -0.0003

Data Index: 835014 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0512. Min Act: -0.0003

Data Index: 21033 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0491. Min Act: -0.0003

Data Index: 898077 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1176715 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0488. Min Act: -0.0003

Data Index: 398842 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0471. Min Act: -0.0003

Data Index: 543752 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1328312 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0468. Min Act: -0.0003

Data Index: 564696 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0504. Min Act: -0.0003

Data Index: 378240 (C4 (Web Text))

Max Activating Token Index: 120