< Prev | Home | Model | Random | Next >

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

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

Neuron 1559 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: 4.1060. Min Range: -4.1060

Max Act: 4.0747. Min Act: -0.1700

Data Index: 921764 (C4 (Web Text))

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.1060. Min Range: -4.1060

Max Act: 4.1060. Min Act: -0.1700

Data Index: 1262962 (C4 (Web Text))

Max Activating Token Index: 781

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.1060. Min Range: -4.1060

Max Act: 4.1060. Min Act: -0.1700

Data Index: 487770 (C4 (Web Text))

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.1060. Min Range: -4.1060

Max Act: 4.1060. Min Act: -0.1700

Data Index: 408471 (C4 (Web Text))

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.1060. Min Range: -4.1060

Max Act: 4.0434. Min Act: -0.1700

Data Index: 1543861 (Python Code)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.1060. Min Range: -4.1060

Max Act: 4.1060. Min Act: -0.1700

Data Index: 535086 (C4 (Web Text))

Max Activating Token Index: 1010

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.1060. Min Range: -4.1060

Max Act: 4.0434. Min Act: -0.1700

Data Index: 419138 (C4 (Web Text))

Max Activating Token Index: 371

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.1060. Min Range: -4.1060

Max Act: 4.0122. Min Act: -0.1700

Data Index: 859912 (C4 (Web Text))

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.1060. Min Range: -4.1060

Max Act: 4.0122. Min Act: -0.1700

Data Index: 778279 (C4 (Web Text))

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.1060. Min Range: -4.1060

Max Act: 4.0122. Min Act: -0.1700

Data Index: 1274617 (C4 (Web Text))

Max Activating Token Index: 525

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.9809. Min Act: -0.1700

Data Index: 367893 (C4 (Web Text))

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.9496. Min Act: -0.1700

Data Index: 1313803 (C4 (Web Text))

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.1060. Min Range: -4.1060

Max Act: 4.0122. Min Act: -0.1700

Data Index: 1122327 (C4 (Web Text))

Max Activating Token Index: 138

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.9809. Min Act: -0.1700

Data Index: 647011 (C4 (Web Text))

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.9496. Min Act: -0.1700

Data Index: 1502359 (Python Code)

Max Activating Token Index: 995

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.9809. Min Act: -0.1700

Data Index: 391282 (C4 (Web Text))

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.9496. Min Act: -0.1700

Data Index: 681997 (C4 (Web Text))

Max Activating Token Index: 578

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.9184. Min Act: -0.1700

Data Index: 214798 (C4 (Web Text))

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.9809. Min Act: -0.1700

Data Index: 673067 (C4 (Web Text))

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.9496. Min Act: -0.1700

Data Index: 1628383 (Python Code)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #19