< Prev | Home | Model | Random | Next >

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

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

Neuron 745 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.8996. Min Act: -0.1700

Data Index: 641888 (C4 (Web Text))

Max Activating Token Index: 990

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.7746. Min Act: -0.1700

Data Index: 1152786 (C4 (Web Text))

Max Activating Token Index: 133

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.7121. Min Act: -0.1700

Data Index: 46576 (C4 (Web Text))

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.7121. Min Act: -0.1699

Data Index: 1047976 (C4 (Web Text))

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.7121. Min Act: -0.1700

Data Index: 988325 (C4 (Web Text))

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.6809. Min Act: -0.1700

Data Index: 342172 (C4 (Web Text))

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.6184. Min Act: -0.1700

Data Index: 196370 (C4 (Web Text))

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.6184. Min Act: -0.1700

Data Index: 1453574 (Python Code)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.6496. Min Act: -0.1700

Data Index: 681975 (C4 (Web Text))

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.6184. Min Act: -0.1700

Data Index: 190228 (C4 (Web Text))

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.6496. Min Act: -0.1700

Data Index: 1223332 (C4 (Web Text))

Max Activating Token Index: 492

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.5871. Min Act: -0.1700

Data Index: 601962 (C4 (Web Text))

Max Activating Token Index: 319

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.5559. Min Act: -0.1700

Data Index: 112597 (C4 (Web Text))

Max Activating Token Index: 736

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.5871. Min Act: -0.1700

Data Index: 1125034 (C4 (Web Text))

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.5559. Min Act: -0.1700

Data Index: 996796 (C4 (Web Text))

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.5559. Min Act: -0.1699

Data Index: 1079010 (C4 (Web Text))

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.5559. Min Act: -0.1699

Data Index: 568607 (C4 (Web Text))

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.4934. Min Act: -0.1699

Data Index: 619618 (C4 (Web Text))

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.4934. Min Act: -0.1700

Data Index: 1627525 (Python Code)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.8996. Min Range: -4.8996

Max Act: 4.5246. Min Act: -0.1700

Data Index: 1503919 (Python Code)

Max Activating Token Index: 553

Click toggle to see full text

Truncated

Full Text #19