< Prev | Home | Model | Random | Next >

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

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

Neuron 308 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.1045. Min Range: -6.1045

Max Act: 6.0889. Min Act: -0.1699

Data Index: 417096 (C4 (Web Text))

Max Activating Token Index: 949

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.1045. Min Range: -6.1045

Max Act: 6.1045. Min Act: -0.1699

Data Index: 1264538 (C4 (Web Text))

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.1045. Min Range: -6.1045

Max Act: 6.0108. Min Act: -0.1699

Data Index: 434864 (C4 (Web Text))

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.9170. Min Act: -0.1699

Data Index: 205220 (C4 (Web Text))

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.9170. Min Act: -0.1699

Data Index: 110014 (C4 (Web Text))

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.8389. Min Act: -0.1699

Data Index: 1321982 (C4 (Web Text))

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.9014. Min Act: -0.1699

Data Index: 369587 (C4 (Web Text))

Max Activating Token Index: 401

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.7764. Min Act: -0.1699

Data Index: 669290 (C4 (Web Text))

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.8076. Min Act: -0.1699

Data Index: 829321 (C4 (Web Text))

Max Activating Token Index: 655

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.7451. Min Act: -0.1699

Data Index: 1273746 (C4 (Web Text))

Max Activating Token Index: 932

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.7920. Min Act: -0.1699

Data Index: 414188 (C4 (Web Text))

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.7608. Min Act: -0.1699

Data Index: 154939 (C4 (Web Text))

Max Activating Token Index: 1020

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.6983. Min Act: -0.1699

Data Index: 684501 (C4 (Web Text))

Max Activating Token Index: 553

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.6826. Min Act: -0.1699

Data Index: 1614381 (Python Code)

Max Activating Token Index: 992

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.6670. Min Act: -0.1699

Data Index: 1418392 (Python Code)

Max Activating Token Index: 697

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.6983. Min Act: -0.1699

Data Index: 1229737 (C4 (Web Text))

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.6670. Min Act: -0.1699

Data Index: 289894 (C4 (Web Text))

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.6670. Min Act: -0.1699

Data Index: 922562 (C4 (Web Text))

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.5967. Min Act: -0.1699

Data Index: 627564 (C4 (Web Text))

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.1045. Min Range: -6.1045

Max Act: 5.6670. Min Act: -0.1699

Data Index: 810850 (C4 (Web Text))

Max Activating Token Index: 604

Click toggle to see full text

Truncated

Full Text #19