Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2003 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.6467. Min Act: -0.1700

Data Index: 1423004 (Python Code)

Max Activating Token Index: 475

Text #1

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.5841. Min Act: -0.1700

Data Index: 1591053 (Python Code)

Max Activating Token Index: 688

Text #2

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.5841. Min Act: -0.1700

Data Index: 1543080 (Python Code)

Max Activating Token Index: 724

Text #3

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.5371. Min Act: -0.1700

Data Index: 1428049 (Python Code)

Max Activating Token Index: 52

Text #4

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.5371. Min Act: -0.1700

Data Index: 1604372 (Python Code)

Max Activating Token Index: 746

Text #5

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.5215. Min Act: -0.1700

Data Index: 778669 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.5058. Min Act: -0.1700

Data Index: 1413640 (Python Code)

Max Activating Token Index: 134

Text #7

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4901. Min Act: -0.1700

Data Index: 1543166 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4901. Min Act: -0.1700

Data Index: 1421629 (Python Code)

Max Activating Token Index: 699

Text #9

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4744. Min Act: -0.1700

Data Index: 1488525 (Python Code)

Max Activating Token Index: 49

Text #10

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4588. Min Act: -0.1700

Data Index: 1418756 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4588. Min Act: -0.1700

Data Index: 1505069 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4431. Min Act: -0.1700

Data Index: 1449391 (Python Code)

Max Activating Token Index: 582

Text #13

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4431. Min Act: -0.1700

Data Index: 1408661 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4274. Min Act: -0.1700

Data Index: 1626490 (Python Code)

Max Activating Token Index: 482

Text #15

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4431. Min Act: -0.1700

Data Index: 1365346 (Python Code)

Max Activating Token Index: 893

Text #16

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4431. Min Act: -0.1700

Data Index: 1467470 (Python Code)

Max Activating Token Index: 864

Text #17

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4274. Min Act: -0.1700

Data Index: 1564059 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4274. Min Act: -0.1700

Data Index: 1578674 (Python Code)

Max Activating Token Index: 792

Text #19

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4117. Min Act: -0.1700

Data Index: 1473843 (Python Code)

Max Activating Token Index: 31