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

Dataset: Open Web Text

Neuron 2020 in Layer 3

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: 4.1889. Min Range: -4.1889

Max Act: 4.1674. Min Act: -0.1700

Data Index: 5288420 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.1361. Min Act: -0.1700

Data Index: 5992649 (Open Web Text)

Max Activating Token Index: 757

Text #2

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.1889. Min Act: -0.1700

Data Index: 2356129 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0820. Min Act: -0.1700

Data Index: 797328 (Open Web Text)

Max Activating Token Index: 167

Text #4

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0377. Min Act: -0.1700

Data Index: 1532350 (Open Web Text)

Max Activating Token Index: 598

Text #5

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0692. Min Act: -0.1700

Data Index: 4104379 (Open Web Text)

Max Activating Token Index: 602

Text #6

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.1136. Min Act: -0.1700

Data Index: 3359854 (Open Web Text)

Max Activating Token Index: 512

Text #7

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0492. Min Act: -0.1700

Data Index: 146404 (Open Web Text)

Max Activating Token Index: 597

Text #8

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0722. Min Act: -0.1700

Data Index: 2305697 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.1098. Min Act: -0.1700

Data Index: 2192545 (Open Web Text)

Max Activating Token Index: 892

Text #10

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0615. Min Act: -0.1700

Data Index: 4841515 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0664. Min Act: -0.1700

Data Index: 7837365 (Open Web Text)

Max Activating Token Index: 512

Text #12

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.1008. Min Act: -0.1700

Data Index: 1361469 (Open Web Text)

Max Activating Token Index: 731

Text #13

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0615. Min Act: -0.1700

Data Index: 7629000 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0193. Min Act: -0.1700

Data Index: 2995963 (Open Web Text)

Max Activating Token Index: 194

Text #15

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0915. Min Act: -0.1700

Data Index: 8452236 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0895. Min Act: -0.1700

Data Index: 8504735 (Open Web Text)

Max Activating Token Index: 782

Text #17

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0722. Min Act: -0.1700

Data Index: 1591202 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0597. Min Act: -0.1700

Data Index: 2696535 (Open Web Text)

Max Activating Token Index: 149

Text #19

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0548. Min Act: -0.1700

Data Index: 5500721 (Open Web Text)

Max Activating Token Index: 5