< Prev | Home | Model | Random | Next >

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

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

Neuron 1470 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: 6.0676. Min Range: -6.0676

Max Act: 6.0676. Min Act: -0.1699

Data Index: 1406912 (Python Code)

Max Activating Token Index: 148

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.0676. Min Range: -6.0676

Max Act: 6.0051. Min Act: -0.1695

Data Index: 1616734 (Python Code)

Max Activating Token Index: 807

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.0676. Min Range: -6.0676

Max Act: 6.0051. Min Act: -0.1700

Data Index: 1411657 (Python Code)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.9426. Min Act: -0.1700

Data Index: 1612406 (Python Code)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.0676. Min Range: -6.0676

Max Act: 6.0051. Min Act: -0.1700

Data Index: 1360382 (Python Code)

Max Activating Token Index: 626

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.8801. Min Act: -0.1700

Data Index: 1541022 (Python Code)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.9113. Min Act: -0.1700

Data Index: 1567395 (Python Code)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.8176. Min Act: -0.1691

Data Index: 1424274 (Python Code)

Max Activating Token Index: 325

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.7238. Min Act: -0.1700

Data Index: 1444105 (Python Code)

Max Activating Token Index: 190

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.7863. Min Act: -0.1696

Data Index: 1454985 (Python Code)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.7551. Min Act: -0.1700

Data Index: 1500513 (Python Code)

Max Activating Token Index: 713

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.6926. Min Act: -0.1695

Data Index: 1390147 (Python Code)

Max Activating Token Index: 655

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.7238. Min Act: -0.1700

Data Index: 1590451 (Python Code)

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.6926. Min Act: -0.1659

Data Index: 1488842 (Python Code)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.6613. Min Act: -0.1700

Data Index: 1566295 (Python Code)

Max Activating Token Index: 840

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.6613. Min Act: -0.1520

Data Index: 526872 (C4 (Web Text))

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.6613. Min Act: -0.1700

Data Index: 377101 (C4 (Web Text))

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.6301. Min Act: -0.1698

Data Index: 1554001 (Python Code)

Max Activating Token Index: 70

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.6613. Min Act: -0.1700

Data Index: 1578987 (Python Code)

Max Activating Token Index: 46

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.0676. Min Range: -6.0676

Max Act: 5.6613. Min Act: -0.1700

Data Index: 1524196 (Python Code)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #19