< Prev | Home | Model | Random | Next >

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

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

Neuron 1455 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: 5.0474. Min Range: -5.0474

Max Act: 5.0474. Min Act: -0.1700

Data Index: 449552 (C4 (Web Text))

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.8911. Min Act: -0.1700

Data Index: 1529151 (Python Code)

Max Activating Token Index: 82

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.8286. Min Act: -0.1700

Data Index: 468228 (C4 (Web Text))

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.8599. Min Act: -0.1700

Data Index: 1650016 (Python Code)

Max Activating Token Index: 736

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.8286. Min Act: -0.1700

Data Index: 1589402 (Python Code)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.8286. Min Act: -0.1700

Data Index: 1560862 (Python Code)

Max Activating Token Index: 707

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.8286. Min Act: -0.1700

Data Index: 1415401 (Python Code)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.8599. Min Act: -0.1700

Data Index: 1579539 (Python Code)

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.8286. Min Act: -0.1700

Data Index: 1404001 (Python Code)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.7661. Min Act: -0.1700

Data Index: 1493689 (Python Code)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.8286. Min Act: -0.1700

Data Index: 1429060 (Python Code)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.7974. Min Act: -0.1700

Data Index: 1612539 (Python Code)

Max Activating Token Index: 663

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.7974. Min Act: -0.1700

Data Index: 1425720 (Python Code)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.8286. Min Act: -0.1700

Data Index: 1604554 (Python Code)

Max Activating Token Index: 890

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.8599. Min Act: -0.1700

Data Index: 1598905 (Python Code)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.7974. Min Act: -0.1700

Data Index: 1561679 (Python Code)

Max Activating Token Index: 204

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.7974. Min Act: -0.1700

Data Index: 1533524 (Python Code)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.7661. Min Act: -0.1700

Data Index: 1443091 (Python Code)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.7661. Min Act: -0.1700

Data Index: 1443298 (Python Code)

Max Activating Token Index: 51

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.7661. Min Act: -0.1700

Data Index: 1453066 (Python Code)

Max Activating Token Index: 156

Click toggle to see full text

Truncated

Full Text #19