< Prev | Home | Model | Random | Next >

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

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

Neuron 1536 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.3125. Min Act: -0.1700

Data Index: 1656910 (Python Code)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.2301. Min Act: -0.1700

Data Index: 1431978 (Python Code)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.2135. Min Act: -0.1700

Data Index: 1491137 (Python Code)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.1804. Min Act: -0.1700

Data Index: 810945 (C4 (Web Text))

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.1804. Min Act: -0.1700

Data Index: 1444950 (Python Code)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.1804. Min Act: -0.1700

Data Index: 873368 (C4 (Web Text))

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.1637. Min Act: -0.1700

Data Index: 1477636 (Python Code)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.1637. Min Act: -0.1700

Data Index: 1496551 (Python Code)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.1471. Min Act: -0.1700

Data Index: 1526706 (Python Code)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.1471. Min Act: -0.1700

Data Index: 1549494 (Python Code)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.1137. Min Act: -0.1700

Data Index: 1629359 (Python Code)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.1304. Min Act: -0.1700

Data Index: 1552116 (Python Code)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.0970. Min Act: -0.1700

Data Index: 1375743 (Python Code)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.0802. Min Act: -0.1700

Data Index: 1434506 (Python Code)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.0802. Min Act: -0.1700

Data Index: 1557332 (Python Code)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.0886. Min Act: -0.1700

Data Index: 1449653 (Python Code)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.0886. Min Act: -0.1700

Data Index: 1637405 (Python Code)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.0719. Min Act: -0.1700

Data Index: 1578089 (Python Code)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.0635. Min Act: -0.1700

Data Index: 1610966 (Python Code)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.3125. Min Range: -2.3125

Max Act: 2.0719. Min Act: -0.1700

Data Index: 1529393 (Python Code)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #19