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

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

Neuron 226 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0671. Min Act: -0.0003

Data Index: 926349 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0619. Min Act: -0.0003

Data Index: 622185 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0563. Min Act: -0.0003

Data Index: 93837 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0561. Min Act: -0.0003

Data Index: 60716 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0602. Min Act: -0.0003

Data Index: 39473 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0562. Min Act: -0.0003

Data Index: 813763 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0585. Min Act: -0.0003

Data Index: 612237 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0582. Min Act: -0.0003

Data Index: 1113738 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0522. Min Act: -0.0003

Data Index: 454252 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1013792 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1284376 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1072630 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0470. Min Act: -0.0003

Data Index: 373500 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0540. Min Act: -0.0003

Data Index: 182810 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0513. Min Act: -0.0003

Data Index: 72836 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0461. Min Act: -0.0003

Data Index: 1287752 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0504. Min Act: -0.0003

Data Index: 94676 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0476. Min Act: -0.0003

Data Index: 418010 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0483. Min Act: -0.0003

Data Index: 735375 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0496. Min Act: -0.0003

Data Index: 539064 (C4 (Web Text))

Max Activating Token Index: 430