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

Dataset: Open Web Text

Neuron 3049 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: 4.0129. Min Range: -4.0129

Max Act: 3.9781. Min Act: -0.1700

Data Index: 7936306 (Open Web Text)

Max Activating Token Index: 557

Text #1

Max Range: 4.0129. Min Range: -4.0129

Max Act: 4.0129. Min Act: -0.1700

Data Index: 2709001 (Open Web Text)

Max Activating Token Index: 564

Text #2

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.9721. Min Act: -0.1700

Data Index: 4610485 (Open Web Text)

Max Activating Token Index: 541

Text #3

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8557. Min Act: -0.1700

Data Index: 3748017 (Open Web Text)

Max Activating Token Index: 933

Text #4

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8917. Min Act: -0.1700

Data Index: 2984729 (Open Web Text)

Max Activating Token Index: 899

Text #5

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8474. Min Act: -0.1700

Data Index: 7788531 (Open Web Text)

Max Activating Token Index: 568

Text #6

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8430. Min Act: -0.1700

Data Index: 4915403 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8472. Min Act: -0.1700

Data Index: 729866 (Open Web Text)

Max Activating Token Index: 877

Text #8

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8514. Min Act: -0.1700

Data Index: 4647373 (Open Web Text)

Max Activating Token Index: 973

Text #9

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8516. Min Act: -0.1700

Data Index: 2551424 (Open Web Text)

Max Activating Token Index: 345

Text #10

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8476. Min Act: -0.1700

Data Index: 4466084 (Open Web Text)

Max Activating Token Index: 909

Text #11

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8453. Min Act: -0.1700

Data Index: 7986459 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8285. Min Act: -0.1700

Data Index: 4260109 (Open Web Text)

Max Activating Token Index: 495

Text #13

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8655. Min Act: -0.1700

Data Index: 1436141 (Open Web Text)

Max Activating Token Index: 544

Text #14

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8606. Min Act: -0.1700

Data Index: 6847582 (Open Web Text)

Max Activating Token Index: 535

Text #15

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8424. Min Act: -0.1700

Data Index: 680256 (Open Web Text)

Max Activating Token Index: 545

Text #16

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8073. Min Act: -0.1700

Data Index: 2621343 (Open Web Text)

Max Activating Token Index: 836

Text #17

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.7808. Min Act: -0.1700

Data Index: 768002 (Open Web Text)

Max Activating Token Index: 636

Text #18

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8491. Min Act: -0.1700

Data Index: 3365683 (Open Web Text)

Max Activating Token Index: 750

Text #19

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8034. Min Act: -0.1700

Data Index: 3391279 (Open Web Text)

Max Activating Token Index: 477