< Prev | Home | Model | Random | Next >

Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 59 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4872. Min Act: -0.1700

Data Index: 4922117 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4608. Min Act: -0.1700

Data Index: 6152353 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4520. Min Act: -0.1700

Data Index: 1273609 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4520. Min Act: -0.1700

Data Index: 1654050 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4520. Min Act: -0.1700

Data Index: 2226709 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4520. Min Act: -0.1700

Data Index: 2702359 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4520. Min Act: -0.1700

Data Index: 3398038 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4520. Min Act: -0.1700

Data Index: 4128535 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4520. Min Act: -0.1700

Data Index: 8546046 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4520. Min Act: -0.1700

Data Index: 5841386 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4520. Min Act: -0.1700

Data Index: 376031 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4520. Min Act: -0.1700

Data Index: 6342166 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4256. Min Act: -0.1700

Data Index: 5956439 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4256. Min Act: -0.1699

Data Index: 5318721 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4080. Min Act: -0.1700

Data Index: 17645 (Open Web Text)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4080. Min Act: -0.1700

Data Index: 357804 (Open Web Text)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4080. Min Act: -0.1700

Data Index: 219402 (Open Web Text)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4080. Min Act: -0.1700

Data Index: 605651 (Open Web Text)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4080. Min Act: -0.1700

Data Index: 44981 (Open Web Text)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4080. Min Act: -0.1700

Data Index: 367870 (Open Web Text)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #19