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

Dataset: Open Web Text

Neuron 162 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: 4.1390. Min Range: -4.1390

Max Act: 4.1390. Min Act: -0.1700

Data Index: 2010975 (Open Web Text)

Max Activating Token Index: 907

Text #1

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.1343. Min Act: -0.1700

Data Index: 8187926 (Open Web Text)

Max Activating Token Index: 233

Text #2

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.0676. Min Act: -0.1700

Data Index: 7575201 (Open Web Text)

Max Activating Token Index: 56

Text #3

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.0588. Min Act: -0.1700

Data Index: 6822683 (Open Web Text)

Max Activating Token Index: 612

Text #4

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.0433. Min Act: -0.1700

Data Index: 2260606 (Open Web Text)

Max Activating Token Index: 553

Text #5

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.0276. Min Act: -0.1700

Data Index: 7541560 (Open Web Text)

Max Activating Token Index: 600

Text #6

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.0151. Min Act: -0.1700

Data Index: 5441658 (Open Web Text)

Max Activating Token Index: 884

Text #7

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9853. Min Act: -0.1700

Data Index: 5777146 (Open Web Text)

Max Activating Token Index: 183

Text #8

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.0170. Min Act: -0.1700

Data Index: 6673556 (Open Web Text)

Max Activating Token Index: 415

Text #9

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.0036. Min Act: -0.1700

Data Index: 573756 (Open Web Text)

Max Activating Token Index: 367

Text #10

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.0020. Min Act: -0.1700

Data Index: 2083243 (Open Web Text)

Max Activating Token Index: 264

Text #11

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9802. Min Act: -0.1700

Data Index: 4876584 (Open Web Text)

Max Activating Token Index: 361

Text #12

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9611. Min Act: -0.1700

Data Index: 2083481 (Open Web Text)

Max Activating Token Index: 742

Text #13

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9649. Min Act: -0.1700

Data Index: 4826837 (Open Web Text)

Max Activating Token Index: 642

Text #14

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.0162. Min Act: -0.1700

Data Index: 4028066 (Open Web Text)

Max Activating Token Index: 709

Text #15

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9680. Min Act: -0.1700

Data Index: 7334488 (Open Web Text)

Max Activating Token Index: 388

Text #16

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9653. Min Act: -0.1700

Data Index: 3385342 (Open Web Text)

Max Activating Token Index: 896

Text #17

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9793. Min Act: -0.1700

Data Index: 951368 (Open Web Text)

Max Activating Token Index: 495

Text #18

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9788. Min Act: -0.1700

Data Index: 4079962 (Open Web Text)

Max Activating Token Index: 711

Text #19

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9607. Min Act: -0.1700

Data Index: 2739457 (Open Web Text)

Max Activating Token Index: 353