< Prev | Home | Model | Random | Next >

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

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

Neuron 1674 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.2372. Min Range: -6.2372

Max Act: 6.2372. Min Act: -0.1700

Data Index: 353908 (C4 (Web Text))

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.2372. Min Range: -6.2372

Max Act: 6.0809. Min Act: -0.1700

Data Index: 857573 (C4 (Web Text))

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.2372. Min Range: -6.2372

Max Act: 6.0809. Min Act: -0.1700

Data Index: 403439 (C4 (Web Text))

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.2372. Min Range: -6.2372

Max Act: 6.0809. Min Act: -0.1700

Data Index: 261704 (C4 (Web Text))

Max Activating Token Index: 1009

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.9559. Min Act: -0.1700

Data Index: 1470432 (Python Code)

Max Activating Token Index: 990

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.7997. Min Act: -0.1700

Data Index: 637151 (C4 (Web Text))

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.9247. Min Act: -0.1700

Data Index: 1181035 (C4 (Web Text))

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.9247. Min Act: -0.1700

Data Index: 463658 (C4 (Web Text))

Max Activating Token Index: 783

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.7684. Min Act: -0.1700

Data Index: 557188 (C4 (Web Text))

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.6747. Min Act: -0.1700

Data Index: 1109410 (C4 (Web Text))

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.9247. Min Act: -0.1700

Data Index: 819290 (C4 (Web Text))

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.8934. Min Act: -0.1700

Data Index: 1486912 (Python Code)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.6434. Min Act: -0.1700

Data Index: 1308963 (C4 (Web Text))

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.9559. Min Act: -0.1700

Data Index: 319597 (C4 (Web Text))

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.7372. Min Act: -0.1700

Data Index: 858405 (C4 (Web Text))

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.7372. Min Act: -0.1700

Data Index: 1177127 (C4 (Web Text))

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.8934. Min Act: -0.1700

Data Index: 368991 (C4 (Web Text))

Max Activating Token Index: 190

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.9247. Min Act: -0.1700

Data Index: 35538 (C4 (Web Text))

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.6122. Min Act: -0.1700

Data Index: 1116871 (C4 (Web Text))

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.2372. Min Range: -6.2372

Max Act: 5.7372. Min Act: -0.1700

Data Index: 1486308 (Python Code)

Max Activating Token Index: 250

Click toggle to see full text

Truncated

Full Text #19