< Prev | Home | Model | Random | Next >

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

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

Neuron 1176 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: 2.8977. Min Range: -2.8977

Max Act: 2.8977. Min Act: -0.1700

Data Index: 650720 (C4 (Web Text))

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.8660. Min Act: -0.1700

Data Index: 421423 (C4 (Web Text))

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.8342. Min Act: -0.1700

Data Index: 51505 (C4 (Web Text))

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.8024. Min Act: -0.1700

Data Index: 159229 (C4 (Web Text))

Max Activating Token Index: 309

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.8183. Min Act: -0.1700

Data Index: 1422499 (Python Code)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.8024. Min Act: -0.1700

Data Index: 1170606 (C4 (Web Text))

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.8024. Min Act: -0.1700

Data Index: 475490 (C4 (Web Text))

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.7865. Min Act: -0.1700

Data Index: 491790 (C4 (Web Text))

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.7386. Min Act: -0.1700

Data Index: 1257685 (C4 (Web Text))

Max Activating Token Index: 654

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.7705. Min Act: -0.1700

Data Index: 843721 (C4 (Web Text))

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.7226. Min Act: -0.1699

Data Index: 1158551 (C4 (Web Text))

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.7386. Min Act: -0.1700

Data Index: 1566616 (Python Code)

Max Activating Token Index: 247

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.6906. Min Act: -0.1700

Data Index: 851294 (C4 (Web Text))

Max Activating Token Index: 632

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.7386. Min Act: -0.1700

Data Index: 1218016 (C4 (Web Text))

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.6586. Min Act: -0.1700

Data Index: 1220320 (C4 (Web Text))

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.6906. Min Act: -0.1700

Data Index: 38488 (C4 (Web Text))

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.6746. Min Act: -0.1700

Data Index: 156981 (C4 (Web Text))

Max Activating Token Index: 706

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.6586. Min Act: -0.1700

Data Index: 264935 (C4 (Web Text))

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.6586. Min Act: -0.1700

Data Index: 1403576 (Python Code)

Max Activating Token Index: 915

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.8977. Min Range: -2.8977

Max Act: 2.7066. Min Act: -0.1700

Data Index: 455678 (C4 (Web Text))

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #19