Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1561 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0478. Min Act: -0.0006

Data Index: 828506 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0472. Min Act: -0.0005

Data Index: 692547 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0451. Min Act: -0.0005

Data Index: 919539 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0400. Min Act: -0.0006

Data Index: 681853 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0478. Min Act: -0.0006

Data Index: 798417 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0406. Min Act: -0.0006

Data Index: 1258547 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0471. Min Act: -0.0006

Data Index: 120980 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0445. Min Act: -0.0006

Data Index: 503554 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0443. Min Act: -0.0006

Data Index: 640525 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0418. Min Act: -0.0006

Data Index: 1204349 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0425. Min Act: -0.0006

Data Index: 635616 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0440. Min Act: -0.0006

Data Index: 321057 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0430. Min Act: -0.0006

Data Index: 324024 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0413. Min Act: -0.0005

Data Index: 427830 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0422. Min Act: -0.0006

Data Index: 511518 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0402. Min Act: -0.0006

Data Index: 876978 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0430. Min Act: -0.0005

Data Index: 427328 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0410. Min Act: -0.0005

Data Index: 580551 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0389. Min Act: -0.0006

Data Index: 928892 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0397. Min Act: -0.0006

Data Index: 942436 (C4 (Web Text))

Max Activating Token Index: 778