< Prev | Home | Model | Random | Next >

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

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

Neuron 669 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.8086. Min Act: -0.1700

Data Index: 873991 (C4 (Web Text))

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.3399. Min Act: -0.1700

Data Index: 1317543 (C4 (Web Text))

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.1836. Min Act: -0.1700

Data Index: 678463 (C4 (Web Text))

Max Activating Token Index: 131

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.2774. Min Act: -0.1700

Data Index: 194748 (C4 (Web Text))

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.1836. Min Act: -0.1700

Data Index: 162188 (C4 (Web Text))

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.1211. Min Act: -0.1700

Data Index: 1439252 (Python Code)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.2149. Min Act: -0.1700

Data Index: 1348490 (C4 (Web Text))

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.2149. Min Act: -0.1700

Data Index: 645046 (C4 (Web Text))

Max Activating Token Index: 430

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.1211. Min Act: -0.1700

Data Index: 172371 (C4 (Web Text))

Max Activating Token Index: 99

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.1836. Min Act: -0.1700

Data Index: 1619658 (Python Code)

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.1836. Min Act: -0.1700

Data Index: 398493 (C4 (Web Text))

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.1211. Min Act: -0.1700

Data Index: 772740 (C4 (Web Text))

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.0586. Min Act: -0.1700

Data Index: 370309 (C4 (Web Text))

Max Activating Token Index: 343

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.0274. Min Act: -0.1700

Data Index: 441598 (C4 (Web Text))

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.8086. Min Range: -6.8086

Max Act: 5.8086. Min Act: -0.1700

Data Index: 28269 (C4 (Web Text))

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.0899. Min Act: -0.1700

Data Index: 1267120 (C4 (Web Text))

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.1524. Min Act: -0.1700

Data Index: 425828 (C4 (Web Text))

Max Activating Token Index: 703

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.0586. Min Act: -0.1700

Data Index: 115496 (C4 (Web Text))

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.8086. Min Range: -6.8086

Max Act: 5.9336. Min Act: -0.1700

Data Index: 656548 (C4 (Web Text))

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.8086. Min Range: -6.8086

Max Act: 6.0586. Min Act: -0.1700

Data Index: 272610 (C4 (Web Text))

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #19