< Prev | Home | Model | Random | Next >

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

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

Neuron 1433 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.2701. Min Act: -0.1700

Data Index: 909644 (C4 (Web Text))

Max Activating Token Index: 825

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.2701. Min Act: -0.1700

Data Index: 271609 (C4 (Web Text))

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.2371. Min Act: -0.1700

Data Index: 1240588 (C4 (Web Text))

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.1874. Min Act: -0.1700

Data Index: 1006794 (C4 (Web Text))

Max Activating Token Index: 964

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.1874. Min Act: -0.1700

Data Index: 907854 (C4 (Web Text))

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.2040. Min Act: -0.1700

Data Index: 430738 (C4 (Web Text))

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.1208. Min Act: -0.1700

Data Index: 1531436 (Python Code)

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.1208. Min Act: -0.1700

Data Index: 396983 (C4 (Web Text))

Max Activating Token Index: 265

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.1208. Min Act: -0.1698

Data Index: 811091 (C4 (Web Text))

Max Activating Token Index: 382

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.1375. Min Act: -0.1700

Data Index: 31939 (C4 (Web Text))

Max Activating Token Index: 682

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.1208. Min Act: -0.1700

Data Index: 580458 (C4 (Web Text))

Max Activating Token Index: 157

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.1041. Min Act: -0.1700

Data Index: 643292 (C4 (Web Text))

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.0874. Min Act: -0.1700

Data Index: 146432 (C4 (Web Text))

Max Activating Token Index: 156

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.1041. Min Act: -0.1700

Data Index: 878204 (C4 (Web Text))

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.0874. Min Act: -0.1700

Data Index: 1168281 (C4 (Web Text))

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.0706. Min Act: -0.1700

Data Index: 932537 (C4 (Web Text))

Max Activating Token Index: 316

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.0706. Min Act: -0.1700

Data Index: 392938 (C4 (Web Text))

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.0706. Min Act: -0.1700

Data Index: 1421674 (Python Code)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.0706. Min Act: -0.1700

Data Index: 1144684 (C4 (Web Text))

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.2701. Min Range: -2.2701

Max Act: 2.0874. Min Act: -0.1700

Data Index: 138098 (C4 (Web Text))

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #19