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

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

Neuron 1478 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0703. Min Act: -0.0003

Data Index: 546003 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0614. Min Act: -0.0003

Data Index: 56015 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1143319 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0596. Min Act: -0.0003

Data Index: 516617 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0514. Min Act: -0.0003

Data Index: 214219 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0509. Min Act: -0.0003

Data Index: 976374 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0510. Min Act: -0.0003

Data Index: 628508 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0496. Min Act: -0.0002

Data Index: 19150 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0498. Min Act: -0.0002

Data Index: 107778 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0495. Min Act: -0.0003

Data Index: 689148 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0476. Min Act: -0.0003

Data Index: 587335 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0473. Min Act: -0.0002

Data Index: 986063 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0453. Min Act: -0.0003

Data Index: 957411 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0464. Min Act: -0.0002

Data Index: 879383 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1187552 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1177754 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0410. Min Act: -0.0003

Data Index: 389451 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0382. Min Act: -0.0003

Data Index: 251562 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0387. Min Act: -0.0003

Data Index: 359382 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1305272 (C4 (Web Text))

Max Activating Token Index: 993