< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2867 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.1908. Min Act: -0.1700

Data Index: 4686134 (Open Web Text)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.1086. Min Act: -0.1700

Data Index: 6773165 (Open Web Text)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.0897. Min Act: -0.1700

Data Index: 6840931 (Open Web Text)

Max Activating Token Index: 828

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.0649. Min Act: -0.1700

Data Index: 2920417 (Open Web Text)

Max Activating Token Index: 468

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.0518. Min Act: -0.1700

Data Index: 4391871 (Open Web Text)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.0316. Min Act: -0.1700

Data Index: 242075 (Open Web Text)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.0243. Min Act: -0.1700

Data Index: 8231062 (Open Web Text)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.0223. Min Act: -0.1700

Data Index: 4846146 (Open Web Text)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.0275. Min Act: -0.1700

Data Index: 7959610 (Open Web Text)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.0278. Min Act: -0.1700

Data Index: 7843260 (Open Web Text)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.0250. Min Act: -0.1700

Data Index: 3998707 (Open Web Text)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.0252. Min Act: -0.1700

Data Index: 7522458 (Open Web Text)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.1908. Min Range: -2.1908

Max Act: 1.9990. Min Act: -0.1700

Data Index: 4249459 (Open Web Text)

Max Activating Token Index: 51

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.1908. Min Range: -2.1908

Max Act: 1.9979. Min Act: -0.1700

Data Index: 1567009 (Open Web Text)

Max Activating Token Index: 478

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.0157. Min Act: -0.1700

Data Index: 8115007 (Open Web Text)

Max Activating Token Index: 635

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.0123. Min Act: -0.1700

Data Index: 3818829 (Open Web Text)

Max Activating Token Index: 124

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.0179. Min Act: -0.1700

Data Index: 3252847 (Open Web Text)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.0126. Min Act: -0.1700

Data Index: 5257833 (Open Web Text)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.1908. Min Range: -2.1908

Max Act: 1.9955. Min Act: -0.1700

Data Index: 5401688 (Open Web Text)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.1908. Min Range: -2.1908

Max Act: 2.0003. Min Act: -0.1700

Data Index: 6274764 (Open Web Text)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #19