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

Dataset: Open Web Text

Neuron 2716 in Layer 4

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: 4.1502. Min Range: -4.1502

Max Act: 4.1502. Min Act: -0.1700

Data Index: 7555944 (Open Web Text)

Max Activating Token Index: 672

Text #1

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0966. Min Act: -0.1700

Data Index: 4171760 (Open Web Text)

Max Activating Token Index: 503

Text #2

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0559. Min Act: -0.1700

Data Index: 3720442 (Open Web Text)

Max Activating Token Index: 725

Text #3

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0900. Min Act: -0.1700

Data Index: 1107442 (Open Web Text)

Max Activating Token Index: 453

Text #4

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0328. Min Act: -0.1700

Data Index: 7681191 (Open Web Text)

Max Activating Token Index: 1000

Text #5

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0601. Min Act: -0.1700

Data Index: 2253937 (Open Web Text)

Max Activating Token Index: 534

Text #6

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0193. Min Act: -0.1700

Data Index: 5760788 (Open Web Text)

Max Activating Token Index: 695

Text #7

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9906. Min Act: -0.1700

Data Index: 177405 (Open Web Text)

Max Activating Token Index: 337

Text #8

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9979. Min Act: -0.1700

Data Index: 566246 (Open Web Text)

Max Activating Token Index: 740

Text #9

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0130. Min Act: -0.1700

Data Index: 1938732 (Open Web Text)

Max Activating Token Index: 518

Text #10

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0168. Min Act: -0.1700

Data Index: 2809532 (Open Web Text)

Max Activating Token Index: 553

Text #11

Max Range: 4.1502. Min Range: -4.1502

Max Act: 4.0304. Min Act: -0.1700

Data Index: 4526975 (Open Web Text)

Max Activating Token Index: 767

Text #12

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9807. Min Act: -0.1700

Data Index: 4572019 (Open Web Text)

Max Activating Token Index: 429

Text #13

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9817. Min Act: -0.1700

Data Index: 2072251 (Open Web Text)

Max Activating Token Index: 875

Text #14

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9846. Min Act: -0.1700

Data Index: 6717289 (Open Web Text)

Max Activating Token Index: 610

Text #15

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9647. Min Act: -0.1700

Data Index: 3494624 (Open Web Text)

Max Activating Token Index: 328

Text #16

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9751. Min Act: -0.1700

Data Index: 1896884 (Open Web Text)

Max Activating Token Index: 394

Text #17

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9698. Min Act: -0.1700

Data Index: 7626550 (Open Web Text)

Max Activating Token Index: 581

Text #18

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9703. Min Act: -0.1700

Data Index: 2634068 (Open Web Text)

Max Activating Token Index: 368

Text #19

Max Range: 4.1502. Min Range: -4.1502

Max Act: 3.9672. Min Act: -0.1700

Data Index: 2603999 (Open Web Text)

Max Activating Token Index: 294