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

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

Neuron 669 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: 0.0555. Min Range: -0.0555

Max Act: 0.0555. Min Act: -0.0006

Data Index: 581843 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0555. Min Act: -0.0006

Data Index: 596928 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0540. Min Act: -0.0006

Data Index: 64451 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0440. Min Act: -0.0006

Data Index: 364261 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0483. Min Act: -0.0006

Data Index: 888734 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0514. Min Act: -0.0006

Data Index: 820195 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0503. Min Act: -0.0006

Data Index: 118377 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0481. Min Act: -0.0006

Data Index: 410955 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0481. Min Act: -0.0006

Data Index: 885012 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0520. Min Act: -0.0006

Data Index: 356027 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0467. Min Act: -0.0006

Data Index: 531770 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0477. Min Act: -0.0006

Data Index: 46806 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0497. Min Act: -0.0006

Data Index: 745480 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0466. Min Act: -0.0006

Data Index: 364046 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0467. Min Act: -0.0006

Data Index: 31023 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0485. Min Act: -0.0006

Data Index: 262507 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0525. Min Act: -0.0006

Data Index: 435765 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0473. Min Act: -0.0006

Data Index: 727905 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0488. Min Act: -0.0006

Data Index: 548670 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0463. Min Act: -0.0006

Data Index: 2758 (C4 (Web Text))

Max Activating Token Index: 54