< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1137 in Layer 0

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: 2.7403. Min Range: -2.7403

Max Act: 2.7403. Min Act: -0.1700

Data Index: 2747826 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.7337. Min Act: -0.1700

Data Index: 2619849 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.7045. Min Act: -0.1700

Data Index: 4766341 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.7137. Min Act: -0.1700

Data Index: 6514984 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.7280. Min Act: -0.1700

Data Index: 8496182 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.6920. Min Act: -0.1700

Data Index: 5872387 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.7021. Min Act: -0.1700

Data Index: 6652734 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.7043. Min Act: -0.1700

Data Index: 2607407 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.7021. Min Act: -0.1700

Data Index: 5960106 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.7022. Min Act: -0.1700

Data Index: 3433434 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.7043. Min Act: -0.1700

Data Index: 5204465 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.7050. Min Act: -0.1700

Data Index: 8520304 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.7021. Min Act: -0.1700

Data Index: 4586357 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.7021. Min Act: -0.1700

Data Index: 6750751 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.6867. Min Act: -0.1700

Data Index: 5833358 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.6936. Min Act: -0.1700

Data Index: 437279 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.6872. Min Act: -0.1700

Data Index: 6830856 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.6936. Min Act: -0.1700

Data Index: 1120518 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.6886. Min Act: -0.1700

Data Index: 6531614 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.7403. Min Range: -2.7403

Max Act: 2.6817. Min Act: -0.1700

Data Index: 4089998 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #19