< Prev | Home | Model | Random | Next >

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

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

Neuron 1173 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.0650. Min Range: -3.0650

Max Act: 3.0650. Min Act: -0.1700

Data Index: 312850 (C4 (Web Text))

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0650. Min Range: -3.0650

Max Act: 3.0650. Min Act: -0.1700

Data Index: 291666 (C4 (Web Text))

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.9860. Min Act: -0.1700

Data Index: 113039 (C4 (Web Text))

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.9544. Min Act: -0.1700

Data Index: 1454033 (Python Code)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.9860. Min Act: -0.1700

Data Index: 842629 (C4 (Web Text))

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.9544. Min Act: -0.1700

Data Index: 608674 (C4 (Web Text))

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.9068. Min Act: -0.1700

Data Index: 553708 (C4 (Web Text))

Max Activating Token Index: 747

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.9227. Min Act: -0.1700

Data Index: 565144 (C4 (Web Text))

Max Activating Token Index: 149

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.9544. Min Act: -0.1700

Data Index: 886714 (C4 (Web Text))

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.9544. Min Act: -0.1700

Data Index: 134835 (C4 (Web Text))

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.9227. Min Act: -0.1700

Data Index: 1140847 (C4 (Web Text))

Max Activating Token Index: 313

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.8751. Min Act: -0.1700

Data Index: 890213 (C4 (Web Text))

Max Activating Token Index: 468

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.9227. Min Act: -0.1700

Data Index: 863724 (C4 (Web Text))

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.9385. Min Act: -0.1700

Data Index: 1296276 (C4 (Web Text))

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.9227. Min Act: -0.1700

Data Index: 716578 (C4 (Web Text))

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.9068. Min Act: -0.1700

Data Index: 1155869 (C4 (Web Text))

Max Activating Token Index: 154

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.9227. Min Act: -0.1700

Data Index: 284820 (C4 (Web Text))

Max Activating Token Index: 604

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.8910. Min Act: -0.1700

Data Index: 907187 (C4 (Web Text))

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.9068. Min Act: -0.1700

Data Index: 517671 (C4 (Web Text))

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0650. Min Range: -3.0650

Max Act: 2.8751. Min Act: -0.1700

Data Index: 1653815 (Python Code)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #19