< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 19 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.8066. Min Act: -0.1700

Data Index: 2459158 (Open Web Text)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.4629. Min Act: -0.1700

Data Index: 4040814 (Open Web Text)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.4316. Min Act: -0.1700

Data Index: 3073420 (Open Web Text)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.4316. Min Act: -0.1700

Data Index: 1251000 (Open Web Text)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.4316. Min Act: -0.1700

Data Index: 2922614 (Open Web Text)

Max Activating Token Index: 805

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.3691. Min Act: -0.1700

Data Index: 6594628 (Open Web Text)

Max Activating Token Index: 791

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.4004. Min Act: -0.1700

Data Index: 7195389 (Open Web Text)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.4004. Min Act: -0.1700

Data Index: 7387347 (Open Web Text)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.4004. Min Act: -0.1700

Data Index: 5185147 (Open Web Text)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.4004. Min Act: -0.1700

Data Index: 3182816 (Open Web Text)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.3691. Min Act: -0.1700

Data Index: 4157108 (Open Web Text)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.3691. Min Act: -0.1700

Data Index: 2020554 (Open Web Text)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.3379. Min Act: -0.1700

Data Index: 6382096 (Open Web Text)

Max Activating Token Index: 303

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.3379. Min Act: -0.1700

Data Index: 752502 (Open Web Text)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.3379. Min Act: -0.1700

Data Index: 3855918 (Open Web Text)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.3379. Min Act: -0.1700

Data Index: 1858488 (Open Web Text)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.3066. Min Act: -0.1700

Data Index: 5295384 (Open Web Text)

Max Activating Token Index: 233

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.3066. Min Act: -0.1700

Data Index: 6599115 (Open Web Text)

Max Activating Token Index: 985

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.2754. Min Act: -0.1700

Data Index: 5670931 (Open Web Text)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.8066. Min Range: -5.8066

Max Act: 5.2754. Min Act: -0.1700

Data Index: 5914443 (Open Web Text)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #19