< Prev | Home | Model | Random | Next >

Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 972 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')



Text #0

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6551. Min Act: -0.1700

Data Index: 1420542 (Python Code)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.5614. Min Act: -0.1700

Data Index: 1058035 (C4 (Web Text))

Max Activating Token Index: 840

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6864. Min Act: -0.1700

Data Index: 1468431 (Python Code)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6239. Min Act: -0.1700

Data Index: 249941 (C4 (Web Text))

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6239. Min Act: -0.1700

Data Index: 1449330 (Python Code)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6239. Min Act: -0.1700

Data Index: 1632757 (Python Code)

Max Activating Token Index: 419

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6551. Min Act: -0.1700

Data Index: 1514611 (Python Code)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6551. Min Act: -0.1700

Data Index: 1363382 (Python Code)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6864. Min Act: -0.1700

Data Index: 1372359 (Python Code)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6239. Min Act: -0.1700

Data Index: 1559278 (Python Code)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.7176. Min Act: -0.1700

Data Index: 1449800 (Python Code)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.5614. Min Act: -0.1700

Data Index: 1602647 (Python Code)

Max Activating Token Index: 182

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.4989. Min Act: -0.1700

Data Index: 1629306 (Python Code)

Max Activating Token Index: 87

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.5301. Min Act: -0.1700

Data Index: 1451134 (Python Code)

Max Activating Token Index: 779

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.4676. Min Act: -0.1700

Data Index: 1449708 (Python Code)

Max Activating Token Index: 106

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.5301. Min Act: -0.1700

Data Index: 1626001 (Python Code)

Max Activating Token Index: 185

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.5614. Min Act: -0.1700

Data Index: 1540194 (Python Code)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6239. Min Act: -0.1700

Data Index: 1530293 (Python Code)

Max Activating Token Index: 687

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.4989. Min Act: -0.1700

Data Index: 1481730 (Python Code)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6239. Min Act: -0.1700

Data Index: 1583910 (Python Code)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #19