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

Dataset: Open Web Text

Neuron 2003 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: 3.9150. Min Range: -3.9150

Max Act: 3.9150. Min Act: -0.1700

Data Index: 3029627 (Open Web Text)

Max Activating Token Index: 768

Text #1

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.8136. Min Act: -0.1700

Data Index: 6899896 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.7342. Min Act: -0.1700

Data Index: 7907579 (Open Web Text)

Max Activating Token Index: 612

Text #3

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.7308. Min Act: -0.1700

Data Index: 7057492 (Open Web Text)

Max Activating Token Index: 366

Text #4

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.7434. Min Act: -0.1700

Data Index: 7557456 (Open Web Text)

Max Activating Token Index: 694

Text #5

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.7453. Min Act: -0.1700

Data Index: 6839286 (Open Web Text)

Max Activating Token Index: 361

Text #6

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.7374. Min Act: -0.1700

Data Index: 3490743 (Open Web Text)

Max Activating Token Index: 418

Text #7

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.7027. Min Act: -0.1700

Data Index: 5134386 (Open Web Text)

Max Activating Token Index: 289

Text #8

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.7093. Min Act: -0.1700

Data Index: 8487950 (Open Web Text)

Max Activating Token Index: 520

Text #9

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.6967. Min Act: -0.1700

Data Index: 4788613 (Open Web Text)

Max Activating Token Index: 910

Text #10

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.6923. Min Act: -0.1700

Data Index: 7390636 (Open Web Text)

Max Activating Token Index: 98

Text #11

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.6773. Min Act: -0.1700

Data Index: 7390487 (Open Web Text)

Max Activating Token Index: 149

Text #12

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.6809. Min Act: -0.1700

Data Index: 1173939 (Open Web Text)

Max Activating Token Index: 744

Text #13

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.6667. Min Act: -0.1700

Data Index: 6402435 (Open Web Text)

Max Activating Token Index: 919

Text #14

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.6578. Min Act: -0.1700

Data Index: 4746412 (Open Web Text)

Max Activating Token Index: 688

Text #15

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.6628. Min Act: -0.1700

Data Index: 8286340 (Open Web Text)

Max Activating Token Index: 421

Text #16

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.6571. Min Act: -0.1700

Data Index: 7965313 (Open Web Text)

Max Activating Token Index: 745

Text #17

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.6521. Min Act: -0.1700

Data Index: 4972329 (Open Web Text)

Max Activating Token Index: 679

Text #18

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.6461. Min Act: -0.1700

Data Index: 567277 (Open Web Text)

Max Activating Token Index: 64

Text #19

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.6362. Min Act: -0.1700

Data Index: 4663459 (Open Web Text)

Max Activating Token Index: 852