< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1910 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.8682. Min Act: -0.1700

Data Index: 3783448 (Open Web Text)

Max Activating Token Index: 380

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.8832. Min Act: -0.1700

Data Index: 3020292 (Open Web Text)

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.8003. Min Act: -0.1700

Data Index: 7270743 (Open Web Text)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.7801. Min Act: -0.1700

Data Index: 2463499 (Open Web Text)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.7193. Min Act: -0.1700

Data Index: 590089 (Open Web Text)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.6982. Min Act: -0.1700

Data Index: 140519 (Open Web Text)

Max Activating Token Index: 947

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.6784. Min Act: -0.1700

Data Index: 1813823 (Open Web Text)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.6508. Min Act: -0.1700

Data Index: 6569224 (Open Web Text)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.6440. Min Act: -0.1700

Data Index: 6896864 (Open Web Text)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.6077. Min Act: -0.1700

Data Index: 6390288 (Open Web Text)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.6155. Min Act: -0.1700

Data Index: 7214695 (Open Web Text)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.5948. Min Act: -0.1700

Data Index: 7290857 (Open Web Text)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.6414. Min Act: -0.1700

Data Index: 6411800 (Open Web Text)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.5903. Min Act: -0.1700

Data Index: 1036117 (Open Web Text)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.5855. Min Act: -0.1700

Data Index: 6436974 (Open Web Text)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.6082. Min Act: -0.1700

Data Index: 583324 (Open Web Text)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.5860. Min Act: -0.1700

Data Index: 4963014 (Open Web Text)

Max Activating Token Index: 565

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.6034. Min Act: -0.1700

Data Index: 675394 (Open Web Text)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.5676. Min Act: -0.1700

Data Index: 4245452 (Open Web Text)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.8832. Min Range: -4.8832

Max Act: 4.5434. Min Act: -0.1700

Data Index: 1909818 (Open Web Text)

Max Activating Token Index: 602

Click toggle to see full text

Truncated

Full Text #19