Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1654 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3105. Min Range: -5.3105

Max Act: 5.3105. Min Act: -0.1700

Data Index: 1373214 (Python Code)

Max Activating Token Index: 748

Text #1

Max Range: 5.3105. Min Range: -5.3105

Max Act: 5.2792. Min Act: -0.1700

Data Index: 1384980 (Python Code)

Max Activating Token Index: 766

Text #2

Max Range: 5.3105. Min Range: -5.3105

Max Act: 5.2792. Min Act: -0.1700

Data Index: 1379307 (Python Code)

Max Activating Token Index: 725

Text #3

Max Range: 5.3105. Min Range: -5.3105

Max Act: 5.1855. Min Act: -0.1700

Data Index: 1502333 (Python Code)

Max Activating Token Index: 577

Text #4

Max Range: 5.3105. Min Range: -5.3105

Max Act: 5.1855. Min Act: -0.1700

Data Index: 1463520 (Python Code)

Max Activating Token Index: 660

Text #5

Max Range: 5.3105. Min Range: -5.3105

Max Act: 5.1542. Min Act: -0.1700

Data Index: 1532676 (Python Code)

Max Activating Token Index: 954

Text #6

Max Range: 5.3105. Min Range: -5.3105

Max Act: 5.1542. Min Act: -0.1700

Data Index: 1603016 (Python Code)

Max Activating Token Index: 565

Text #7

Max Range: 5.3105. Min Range: -5.3105

Max Act: 5.1230. Min Act: -0.1700

Data Index: 1374914 (Python Code)

Max Activating Token Index: 488

Text #8

Max Range: 5.3105. Min Range: -5.3105

Max Act: 5.1230. Min Act: -0.1700

Data Index: 1362023 (Python Code)

Max Activating Token Index: 586

Text #9

Max Range: 5.3105. Min Range: -5.3105

Max Act: 5.0917. Min Act: -0.1700

Data Index: 1444081 (Python Code)

Max Activating Token Index: 386

Text #10

Max Range: 5.3105. Min Range: -5.3105

Max Act: 5.1230. Min Act: -0.1700

Data Index: 1486755 (Python Code)

Max Activating Token Index: 73

Text #11

Max Range: 5.3105. Min Range: -5.3105

Max Act: 5.0605. Min Act: -0.1700

Data Index: 1369568 (Python Code)

Max Activating Token Index: 453

Text #12

Max Range: 5.3105. Min Range: -5.3105

Max Act: 5.0605. Min Act: -0.1700

Data Index: 1651257 (Python Code)

Max Activating Token Index: 392

Text #13

Max Range: 5.3105. Min Range: -5.3105

Max Act: 5.0292. Min Act: -0.1700

Data Index: 1616131 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 5.3105. Min Range: -5.3105

Max Act: 4.9980. Min Act: -0.1700

Data Index: 1570496 (Python Code)

Max Activating Token Index: 296

Text #15

Max Range: 5.3105. Min Range: -5.3105

Max Act: 4.9980. Min Act: -0.1700

Data Index: 1486977 (Python Code)

Max Activating Token Index: 259

Text #16

Max Range: 5.3105. Min Range: -5.3105

Max Act: 5.0292. Min Act: -0.1700

Data Index: 1373903 (Python Code)

Max Activating Token Index: 45

Text #17

Max Range: 5.3105. Min Range: -5.3105

Max Act: 4.9667. Min Act: -0.1700

Data Index: 1640108 (Python Code)

Max Activating Token Index: 197

Text #18

Max Range: 5.3105. Min Range: -5.3105

Max Act: 4.9667. Min Act: -0.1700

Data Index: 1454893 (Python Code)

Max Activating Token Index: 381

Text #19

Max Range: 5.3105. Min Range: -5.3105

Max Act: 4.9980. Min Act: -0.1700

Data Index: 1519765 (Python Code)

Max Activating Token Index: 661