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

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

Neuron 3202 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.2929. Min Act: -0.0000

Data Index: 1477563 (Python Code)

Max Activating Token Index: 371

Text #1

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.3016. Min Act: -0.0000

Data Index: 1572707 (Python Code)

Max Activating Token Index: 564

Text #2

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1382557 (Python Code)

Max Activating Token Index: 51

Text #3

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.2263. Min Act: -0.0000

Data Index: 1509325 (Python Code)

Max Activating Token Index: 714

Text #4

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.1849. Min Act: -0.0000

Data Index: 1503097 (Python Code)

Max Activating Token Index: 939

Text #5

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.1698. Min Act: -0.0000

Data Index: 1506158 (Python Code)

Max Activating Token Index: 58

Text #6

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0909. Min Act: -0.0000

Data Index: 1443721 (Python Code)

Max Activating Token Index: 161

Text #7

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.1534. Min Act: -0.0000

Data Index: 1606192 (Python Code)

Max Activating Token Index: 805

Text #8

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0869. Min Act: -0.0000

Data Index: 1601723 (Python Code)

Max Activating Token Index: 818

Text #9

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1367654 (Python Code)

Max Activating Token Index: 335

Text #10

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0300. Min Act: -0.0000

Data Index: 1420633 (Python Code)

Max Activating Token Index: 177

Text #11

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1630438 (Python Code)

Max Activating Token Index: 831

Text #12

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0170. Min Act: -0.0000

Data Index: 1376415 (Python Code)

Max Activating Token Index: 155

Text #13

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0836. Min Act: -0.0000

Data Index: 1371139 (Python Code)

Max Activating Token Index: 569

Text #14

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0356. Min Act: -0.0000

Data Index: 1612265 (Python Code)

Max Activating Token Index: 941

Text #15

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0663. Min Act: -0.0000

Data Index: 1513568 (Python Code)

Max Activating Token Index: 395

Text #16

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0589. Min Act: -0.0000

Data Index: 1546184 (Python Code)

Max Activating Token Index: 354

Text #17

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0630. Min Act: -0.0000

Data Index: 1654825 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1516140 (Python Code)

Max Activating Token Index: 1014

Text #19

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9009. Min Act: -0.0000

Data Index: 1638540 (Python Code)

Max Activating Token Index: 300