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

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

Neuron 589 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: 0.0605. Min Range: -0.0605

Max Act: 0.0575. Min Act: -0.0003

Data Index: 513835 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0565. Min Act: -0.0003

Data Index: 822210 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0605. Min Act: -0.0003

Data Index: 1265426 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0532. Min Act: -0.0003

Data Index: 685200 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0547. Min Act: -0.0003

Data Index: 235314 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0507. Min Act: -0.0003

Data Index: 872265 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1092690 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0519. Min Act: -0.0003

Data Index: 323054 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0506. Min Act: -0.0003

Data Index: 1126031 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1047617 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0457. Min Act: -0.0003

Data Index: 351497 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0438. Min Act: -0.0003

Data Index: 655980 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0438. Min Act: -0.0003

Data Index: 576071 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1182433 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0418. Min Act: -0.0003

Data Index: 1328497 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0482. Min Act: -0.0003

Data Index: 789622 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1191778 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0474. Min Act: -0.0003

Data Index: 1023511 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0481. Min Act: -0.0003

Data Index: 805477 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0412. Min Act: -0.0003

Data Index: 797117 (C4 (Web Text))

Max Activating Token Index: 261