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

Dataset: Open Web Text

Neuron 2784 in Layer 5

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: 3.7889. Min Range: -3.7889

Max Act: 3.7889. Min Act: -0.1700

Data Index: 4798573 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.7567. Min Act: -0.1700

Data Index: 8029345 (Open Web Text)

Max Activating Token Index: 928

Text #2

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.7354. Min Act: -0.1700

Data Index: 6500939 (Open Web Text)

Max Activating Token Index: 303

Text #3

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.7258. Min Act: -0.1700

Data Index: 5460257 (Open Web Text)

Max Activating Token Index: 18

Text #4

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.7118. Min Act: -0.1700

Data Index: 3505243 (Open Web Text)

Max Activating Token Index: 329

Text #5

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.7066. Min Act: -0.1700

Data Index: 6383266 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6861. Min Act: -0.1700

Data Index: 7535185 (Open Web Text)

Max Activating Token Index: 82

Text #7

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6862. Min Act: -0.1700

Data Index: 7740953 (Open Web Text)

Max Activating Token Index: 403

Text #8

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6803. Min Act: -0.1700

Data Index: 6961172 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6816. Min Act: -0.1700

Data Index: 6823773 (Open Web Text)

Max Activating Token Index: 436

Text #10

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6868. Min Act: -0.1700

Data Index: 8247591 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6869. Min Act: -0.1700

Data Index: 1888613 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6437. Min Act: -0.1700

Data Index: 839890 (Open Web Text)

Max Activating Token Index: 523

Text #13

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6726. Min Act: -0.1700

Data Index: 1511304 (Open Web Text)

Max Activating Token Index: 705

Text #14

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6669. Min Act: -0.1700

Data Index: 1288531 (Open Web Text)

Max Activating Token Index: 442

Text #15

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6272. Min Act: -0.1700

Data Index: 2644820 (Open Web Text)

Max Activating Token Index: 733

Text #16

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6422. Min Act: -0.1700

Data Index: 3952197 (Open Web Text)

Max Activating Token Index: 165

Text #17

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6468. Min Act: -0.1700

Data Index: 1383484 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6536. Min Act: -0.1700

Data Index: 7517446 (Open Web Text)

Max Activating Token Index: 479

Text #19

Max Range: 3.7889. Min Range: -3.7889

Max Act: 3.6495. Min Act: -0.1700

Data Index: 617659 (Open Web Text)

Max Activating Token Index: 85