Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3815 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0690. Min Act: -0.0002

Data Index: 543481 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0509. Min Act: -0.0002

Data Index: 276568 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0524. Min Act: -0.0002

Data Index: 330733 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0531. Min Act: -0.0002

Data Index: 231539 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0526. Min Act: -0.0002

Data Index: 720595 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0452. Min Act: -0.0002

Data Index: 156351 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0464. Min Act: -0.0002

Data Index: 845569 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0530. Min Act: -0.0002

Data Index: 557450 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0509. Min Act: -0.0002

Data Index: 105207 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1079555 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0432. Min Act: -0.0002

Data Index: 675006 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0411. Min Act: -0.0002

Data Index: 986577 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1051240 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1080115 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1155415 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0403. Min Act: -0.0002

Data Index: 495743 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0410. Min Act: -0.0002

Data Index: 80272 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0387. Min Act: -0.0002

Data Index: 186847 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0366. Min Act: -0.0002

Data Index: 757338 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0440. Min Act: -0.0002

Data Index: 141105 (C4 (Web Text))

Max Activating Token Index: 610