< Prev | Home | Model | Random | Next >

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

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

Neuron 1087 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 5.0702. Min Range: -5.0702

Max Act: 5.0702. Min Act: -0.1700

Data Index: 1496404 (Python Code)

Max Activating Token Index: 925

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.8984. Min Act: -0.1700

Data Index: 1177587 (C4 (Web Text))

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.8359. Min Act: -0.1700

Data Index: 97978 (C4 (Web Text))

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.7265. Min Act: -0.1700

Data Index: 1085078 (C4 (Web Text))

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.7109. Min Act: -0.1700

Data Index: 2219 (C4 (Web Text))

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.7265. Min Act: -0.1700

Data Index: 661544 (C4 (Web Text))

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.6640. Min Act: -0.1700

Data Index: 73248 (C4 (Web Text))

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.6484. Min Act: -0.1700

Data Index: 1514937 (Python Code)

Max Activating Token Index: 912

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.5859. Min Act: -0.1700

Data Index: 611589 (C4 (Web Text))

Max Activating Token Index: 708

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.6171. Min Act: -0.1700

Data Index: 662155 (C4 (Web Text))

Max Activating Token Index: 252

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.4921. Min Act: -0.1700

Data Index: 752343 (C4 (Web Text))

Max Activating Token Index: 551

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.5390. Min Act: -0.1700

Data Index: 469002 (C4 (Web Text))

Max Activating Token Index: 290

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.4609. Min Act: -0.1700

Data Index: 1018497 (C4 (Web Text))

Max Activating Token Index: 292

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.4921. Min Act: -0.1700

Data Index: 1049297 (C4 (Web Text))

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.4609. Min Act: -0.1700

Data Index: 55424 (C4 (Web Text))

Max Activating Token Index: 682

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.4296. Min Act: -0.1700

Data Index: 7885 (C4 (Web Text))

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.4609. Min Act: -0.1700

Data Index: 1358703 (C4 (Web Text))

Max Activating Token Index: 687

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.4609. Min Act: -0.1700

Data Index: 1555323 (Python Code)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.4140. Min Act: -0.1700

Data Index: 107010 (C4 (Web Text))

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.0702. Min Range: -5.0702

Max Act: 4.3827. Min Act: -0.1700

Data Index: 468517 (C4 (Web Text))

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #19