< Prev | Home | Model | Random | Next >

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

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

Neuron 999 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: 6.2553. Min Range: -6.2553

Max Act: 6.2553. Min Act: -0.1700

Data Index: 1612868 (Python Code)

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.2553. Min Range: -6.2553

Max Act: 6.2553. Min Act: -0.1693

Data Index: 35651 (C4 (Web Text))

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.2553. Min Range: -6.2553

Max Act: 6.2553. Min Act: -0.1698

Data Index: 1344698 (C4 (Web Text))

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.2553. Min Range: -6.2553

Max Act: 6.1928. Min Act: -0.1700

Data Index: 808102 (C4 (Web Text))

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.2553. Min Range: -6.2553

Max Act: 6.0678. Min Act: -0.1700

Data Index: 669313 (C4 (Web Text))

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.2553. Min Range: -6.2553

Max Act: 6.0678. Min Act: -0.1700

Data Index: 844778 (C4 (Web Text))

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.2553. Min Range: -6.2553

Max Act: 6.0053. Min Act: -0.1699

Data Index: 1135930 (C4 (Web Text))

Max Activating Token Index: 663

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.2553. Min Range: -6.2553

Max Act: 6.0053. Min Act: -0.1700

Data Index: 361366 (C4 (Web Text))

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.2553. Min Range: -6.2553

Max Act: 5.9428. Min Act: -0.1190

Data Index: 384714 (C4 (Web Text))

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.2553. Min Range: -6.2553

Max Act: 5.9428. Min Act: -0.1700

Data Index: 1208553 (C4 (Web Text))

Max Activating Token Index: 635

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.2553. Min Range: -6.2553

Max Act: 5.9428. Min Act: -0.1609

Data Index: 565887 (C4 (Web Text))

Max Activating Token Index: 228

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.2553. Min Range: -6.2553

Max Act: 6.0053. Min Act: -0.1700

Data Index: 462346 (C4 (Web Text))

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.2553. Min Range: -6.2553

Max Act: 5.9428. Min Act: -0.1700

Data Index: 171523 (C4 (Web Text))

Max Activating Token Index: 466

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.2553. Min Range: -6.2553

Max Act: 5.9428. Min Act: -0.1699

Data Index: 462600 (C4 (Web Text))

Max Activating Token Index: 801

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.2553. Min Range: -6.2553

Max Act: 5.9428. Min Act: -0.1699

Data Index: 1109125 (C4 (Web Text))

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.2553. Min Range: -6.2553

Max Act: 5.9428. Min Act: -0.1700

Data Index: 784713 (C4 (Web Text))

Max Activating Token Index: 653

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.2553. Min Range: -6.2553

Max Act: 5.9428. Min Act: -0.1700

Data Index: 1339743 (C4 (Web Text))

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.2553. Min Range: -6.2553

Max Act: 5.9428. Min Act: -0.1700

Data Index: 1506021 (Python Code)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.2553. Min Range: -6.2553

Max Act: 5.8803. Min Act: -0.1700

Data Index: 1185913 (C4 (Web Text))

Max Activating Token Index: 473

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.2553. Min Range: -6.2553

Max Act: 5.8803. Min Act: -0.1693

Data Index: 1064021 (C4 (Web Text))

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #19