Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2292 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1445634 (Python Code)

Max Activating Token Index: 659

Text #1

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.8379. Min Act: -0.0000

Data Index: 954534 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.8921. Min Act: -0.0000

Data Index: 862310 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1651700 (Python Code)

Max Activating Token Index: 560

Text #4

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7884. Min Act: -0.0000

Data Index: 1586857 (Python Code)

Max Activating Token Index: 999

Text #5

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7663. Min Act: -0.0000

Data Index: 1285359 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1515734 (Python Code)

Max Activating Token Index: 543

Text #7

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1442660 (Python Code)

Max Activating Token Index: 420

Text #8

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7365. Min Act: -0.0000

Data Index: 1547657 (Python Code)

Max Activating Token Index: 742

Text #9

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1084675 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7271. Min Act: -0.0000

Data Index: 1612983 (Python Code)

Max Activating Token Index: 889

Text #11

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1436656 (Python Code)

Max Activating Token Index: 222

Text #12

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1532978 (Python Code)

Max Activating Token Index: 900

Text #13

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7433. Min Act: -0.0000

Data Index: 324952 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1625774 (Python Code)

Max Activating Token Index: 651

Text #15

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6961. Min Act: -0.0000

Data Index: 1560453 (Python Code)

Max Activating Token Index: 700

Text #16

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1594498 (Python Code)

Max Activating Token Index: 446

Text #17

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6632. Min Act: -0.0000

Data Index: 598904 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1575060 (Python Code)

Max Activating Token Index: 912

Text #19

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1514279 (Python Code)

Max Activating Token Index: 674