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

Dataset: Open Web Text

Neuron 2834 in Layer 6

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: 5.9479. Min Range: -5.9479

Max Act: 5.9479. Min Act: -0.1700

Data Index: 5555807 (Open Web Text)

Max Activating Token Index: 538

Text #1

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.6823. Min Act: -0.1700

Data Index: 8350800 (Open Web Text)

Max Activating Token Index: 462

Text #2

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.6439. Min Act: -0.1700

Data Index: 1135140 (Open Web Text)

Max Activating Token Index: 932

Text #3

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.6504. Min Act: -0.1700

Data Index: 2874620 (Open Web Text)

Max Activating Token Index: 149

Text #4

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.5848. Min Act: -0.1700

Data Index: 8631185 (Open Web Text)

Max Activating Token Index: 825

Text #5

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.5481. Min Act: -0.1700

Data Index: 6674125 (Open Web Text)

Max Activating Token Index: 181

Text #6

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.5389. Min Act: -0.1700

Data Index: 5685701 (Open Web Text)

Max Activating Token Index: 266

Text #7

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.5250. Min Act: -0.1700

Data Index: 7596832 (Open Web Text)

Max Activating Token Index: 513

Text #8

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.4934. Min Act: -0.1700

Data Index: 4565396 (Open Web Text)

Max Activating Token Index: 801

Text #9

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.4927. Min Act: -0.1700

Data Index: 2399972 (Open Web Text)

Max Activating Token Index: 715

Text #10

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.5012. Min Act: -0.1700

Data Index: 1268635 (Open Web Text)

Max Activating Token Index: 470

Text #11

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.4899. Min Act: -0.1700

Data Index: 2356142 (Open Web Text)

Max Activating Token Index: 995

Text #12

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.4552. Min Act: -0.1700

Data Index: 2942109 (Open Web Text)

Max Activating Token Index: 745

Text #13

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.4848. Min Act: -0.1700

Data Index: 458870 (Open Web Text)

Max Activating Token Index: 259

Text #14

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.4595. Min Act: -0.1700

Data Index: 1072087 (Open Web Text)

Max Activating Token Index: 944

Text #15

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.4511. Min Act: -0.1700

Data Index: 361100 (Open Web Text)

Max Activating Token Index: 569

Text #16

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.4185. Min Act: -0.1700

Data Index: 1685537 (Open Web Text)

Max Activating Token Index: 629

Text #17

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.4426. Min Act: -0.1700

Data Index: 7063351 (Open Web Text)

Max Activating Token Index: 960

Text #18

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.4278. Min Act: -0.1700

Data Index: 5967650 (Open Web Text)

Max Activating Token Index: 867

Text #19

Max Range: 5.9479. Min Range: -5.9479

Max Act: 5.3925. Min Act: -0.1700

Data Index: 4604351 (Open Web Text)

Max Activating Token Index: 640