< Prev | Home | Model | Random | Next >

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

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

Neuron 1637 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: 4.9588. Min Range: -4.9588

Max Act: 4.9588. Min Act: -0.1700

Data Index: 940061 (C4 (Web Text))

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.9276. Min Act: -0.1700

Data Index: 1078375 (C4 (Web Text))

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.9276. Min Act: -0.1700

Data Index: 473975 (C4 (Web Text))

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.8651. Min Act: -0.1700

Data Index: 21027 (C4 (Web Text))

Max Activating Token Index: 138

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.8651. Min Act: -0.1700

Data Index: 124582 (C4 (Web Text))

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.9276. Min Act: -0.1700

Data Index: 1336983 (C4 (Web Text))

Max Activating Token Index: 670

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.8338. Min Act: -0.1700

Data Index: 418126 (C4 (Web Text))

Max Activating Token Index: 628

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.8026. Min Act: -0.1700

Data Index: 344229 (C4 (Web Text))

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.7713. Min Act: -0.1700

Data Index: 841066 (C4 (Web Text))

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.7713. Min Act: -0.1700

Data Index: 926835 (C4 (Web Text))

Max Activating Token Index: 406

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.7713. Min Act: -0.1700

Data Index: 49151 (C4 (Web Text))

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.6463. Min Act: -0.1700

Data Index: 530622 (C4 (Web Text))

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.7088. Min Act: -0.1700

Data Index: 33664 (C4 (Web Text))

Max Activating Token Index: 138

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.5838. Min Act: -0.1700

Data Index: 963191 (C4 (Web Text))

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.5526. Min Act: -0.1700

Data Index: 1431824 (Python Code)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.4901. Min Act: -0.1700

Data Index: 1225528 (C4 (Web Text))

Max Activating Token Index: 630

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.5213. Min Act: -0.1700

Data Index: 1649777 (Python Code)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.5213. Min Act: -0.1700

Data Index: 366850 (C4 (Web Text))

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.5213. Min Act: -0.1700

Data Index: 87743 (C4 (Web Text))

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.9588. Min Range: -4.9588

Max Act: 4.4588. Min Act: -0.1700

Data Index: 1489813 (Python Code)

Max Activating Token Index: 374

Click toggle to see full text

Truncated

Full Text #19