< Prev | Home | Model | Random | Next >

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

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

Neuron 1380 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.5865. Min Act: -0.1700

Data Index: 430263 (C4 (Web Text))

Max Activating Token Index: 868

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.4571. Min Act: -0.1700

Data Index: 1477839 (Python Code)

Max Activating Token Index: 602

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.4571. Min Act: -0.1700

Data Index: 1302444 (C4 (Web Text))

Max Activating Token Index: 676

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.4571. Min Act: -0.1700

Data Index: 1650193 (Python Code)

Max Activating Token Index: 331

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.4246. Min Act: -0.1700

Data Index: 1181975 (C4 (Web Text))

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.4409. Min Act: -0.1700

Data Index: 130622 (C4 (Web Text))

Max Activating Token Index: 440

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.4246. Min Act: -0.1700

Data Index: 94209 (C4 (Web Text))

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.4246. Min Act: -0.1700

Data Index: 640297 (C4 (Web Text))

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.4246. Min Act: -0.1700

Data Index: 1356507 (C4 (Web Text))

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.3920. Min Act: -0.1700

Data Index: 206587 (C4 (Web Text))

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.4246. Min Act: -0.1700

Data Index: 561638 (C4 (Web Text))

Max Activating Token Index: 182

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.4246. Min Act: -0.1700

Data Index: 457397 (C4 (Web Text))

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.4083. Min Act: -0.1700

Data Index: 1648060 (Python Code)

Max Activating Token Index: 200

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.4083. Min Act: -0.1700

Data Index: 261653 (C4 (Web Text))

Max Activating Token Index: 868

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.4083. Min Act: -0.1700

Data Index: 984693 (C4 (Web Text))

Max Activating Token Index: 242

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.3757. Min Act: -0.1700

Data Index: 1113253 (C4 (Web Text))

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.3920. Min Act: -0.1700

Data Index: 507973 (C4 (Web Text))

Max Activating Token Index: 270

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.3920. Min Act: -0.1700

Data Index: 681550 (C4 (Web Text))

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.3920. Min Act: -0.1700

Data Index: 201624 (C4 (Web Text))

Max Activating Token Index: 843

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.5865. Min Range: -2.5865

Max Act: 2.3920. Min Act: -0.1700

Data Index: 160711 (C4 (Web Text))

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #19