Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2603 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1537486 (Python Code)

Max Activating Token Index: 273

Text #1

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0516. Min Act: -0.0001

Data Index: 877151 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0529. Min Act: -0.0001

Data Index: 322294 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0541. Min Act: -0.0002

Data Index: 381571 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0515. Min Act: -0.0002

Data Index: 582049 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0524. Min Act: -0.0002

Data Index: 58399 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0512. Min Act: -0.0002

Data Index: 700965 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0514. Min Act: -0.0001

Data Index: 800294 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0497. Min Act: -0.0001

Data Index: 1177267 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0499. Min Act: -0.0001

Data Index: 68405 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0508. Min Act: -0.0002

Data Index: 182588 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1314478 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0497. Min Act: -0.0001

Data Index: 217252 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0494. Min Act: -0.0001

Data Index: 563408 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0495. Min Act: -0.0002

Data Index: 589873 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0502. Min Act: -0.0001

Data Index: 182005 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0479. Min Act: -0.0002

Data Index: 592113 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0493. Min Act: -0.0002

Data Index: 61127 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1257109 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0489. Min Act: -0.0002

Data Index: 210279 (C4 (Web Text))

Max Activating Token Index: 920